[{"year":"2024","date_created":"2024-03-10T23:00:53Z","citation":{"chicago":"Schmidt, Hauke, Sebastian Rast, Jiawei Bao, Amrit Cassim, Shih Wei Fang, Diego Jimenez-De La Cuesta, Paul Keil, et al. “Effects of Vertical Grid Spacing on the Climate Simulated in the ICON-Sapphire Global Storm-Resolving Model.” <i>Geoscientific Model Development</i>. European Geosciences Union, 2024. <a href=\"https://doi.org/10.5194/gmd-17-1563-2024\">https://doi.org/10.5194/gmd-17-1563-2024</a>.","ista":"Schmidt H, Rast S, Bao J, Cassim A, Fang SW, Jimenez-De La Cuesta D, Keil P, Kluft L, Kroll C, Lang T, Niemeier U, Schneidereit A, Williams AIL, Stevens B. 2024. Effects of vertical grid spacing on the climate simulated in the ICON-Sapphire global storm-resolving model. Geoscientific Model Development. 17(4), 1563–1584.","ieee":"H. Schmidt <i>et al.</i>, “Effects of vertical grid spacing on the climate simulated in the ICON-Sapphire global storm-resolving model,” <i>Geoscientific Model Development</i>, vol. 17, no. 4. European Geosciences Union, pp. 1563–1584, 2024.","mla":"Schmidt, Hauke, et al. “Effects of Vertical Grid Spacing on the Climate Simulated in the ICON-Sapphire Global Storm-Resolving Model.” <i>Geoscientific Model Development</i>, vol. 17, no. 4, European Geosciences Union, 2024, pp. 1563–84, doi:<a href=\"https://doi.org/10.5194/gmd-17-1563-2024\">10.5194/gmd-17-1563-2024</a>.","ama":"Schmidt H, Rast S, Bao J, et al. Effects of vertical grid spacing on the climate simulated in the ICON-Sapphire global storm-resolving model. <i>Geoscientific Model Development</i>. 2024;17(4):1563-1584. doi:<a href=\"https://doi.org/10.5194/gmd-17-1563-2024\">10.5194/gmd-17-1563-2024</a>","short":"H. Schmidt, S. Rast, J. Bao, A. Cassim, S.W. Fang, D. Jimenez-De La Cuesta, P. Keil, L. Kluft, C. Kroll, T. Lang, U. Niemeier, A. Schneidereit, A.I.L. Williams, B. Stevens, Geoscientific Model Development 17 (2024) 1563–1584.","apa":"Schmidt, H., Rast, S., Bao, J., Cassim, A., Fang, S. W., Jimenez-De La Cuesta, D., … Stevens, B. (2024). Effects of vertical grid spacing on the climate simulated in the ICON-Sapphire global storm-resolving model. <i>Geoscientific Model Development</i>. European Geosciences Union. <a href=\"https://doi.org/10.5194/gmd-17-1563-2024\">https://doi.org/10.5194/gmd-17-1563-2024</a>"},"department":[{"_id":"CaMu"}],"status":"public","has_accepted_license":"1","oa":1,"author":[{"full_name":"Schmidt, Hauke","first_name":"Hauke","last_name":"Schmidt"},{"first_name":"Sebastian","last_name":"Rast","full_name":"Rast, Sebastian"},{"full_name":"Bao, Jiawei","last_name":"Bao","id":"bb9a7399-fefd-11ed-be3c-ae648fd1d160","first_name":"Jiawei"},{"full_name":"Cassim, Amrit","last_name":"Cassim","first_name":"Amrit"},{"full_name":"Fang, Shih Wei","first_name":"Shih Wei","last_name":"Fang"},{"last_name":"Jimenez-De La Cuesta","first_name":"Diego","full_name":"Jimenez-De La Cuesta, Diego"},{"full_name":"Keil, Paul","first_name":"Paul","last_name":"Keil"},{"full_name":"Kluft, Lukas","first_name":"Lukas","last_name":"Kluft"},{"full_name":"Kroll, Clarissa","last_name":"Kroll","first_name":"Clarissa"},{"first_name":"Theresa","last_name":"Lang","full_name":"Lang, Theresa"},{"last_name":"Niemeier","first_name":"Ulrike","full_name":"Niemeier, Ulrike"},{"last_name":"Schneidereit","first_name":"Andrea","full_name":"Schneidereit, Andrea"},{"full_name":"Williams, Andrew I.L.","first_name":"Andrew I.L.","last_name":"Williams"},{"first_name":"Bjorn","last_name":"Stevens","full_name":"Stevens, Bjorn"}],"external_id":{"isi":["001190535000001"]},"month":"02","date_updated":"2026-10-01T08:55:28Z","date_published":"2024-02-22T00:00:00Z","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","ddc":["550"],"das_tickbox":"1","supplementarymaterial":"no","intvolume":"        17","publication_identifier":{"issn":["1991-959X"],"eissn":["1991-9603"]},"file_date_updated":"2024-03-13T08:59:21Z","language":[{"iso":"eng"}],"_id":"15097","issue":"4","isi":1,"day":"22","title":"Effects of vertical grid spacing on the climate simulated in the ICON-Sapphire global storm-resolving model","doi":"10.5194/gmd-17-1563-2024","acknowledgement":"The authors wish to thank Ann Kristin Naumann and three anonymous reviewers for very helpful comments on an earlier version of this paper. We are grateful to René Redler and Karl-Hermann Wieners for useful recommendations regarding running the simulations. We thank Luis Kornblueh for providing an external vertical grid generator and resolving the memory requirements for the very fine vertical grids. We acknowledge Hauke Schulz for providing the radiosonde data. The simulations were run at the German Climate Computing Center (DKRZ), and we thank the DKRZ staff for their support.\r\nHauke Schmidt and Diego Jimenez-de la Cuesta received financial support from the SOCTOC project within the framework of the ROMIC program, funded by the German Ministry of Education and Research (BMBF) (grant no. 01LG1903A).\r\nThe article processing charges for this open-access publication were covered by the Max Planck Society.","related_material":{"record":[{"id":"23015","relation":"research_data","status":"public"}]},"file":[{"content_type":"application/pdf","access_level":"open_access","date_updated":"2024-03-13T08:59:21Z","date_created":"2024-03-13T08:59:21Z","relation":"main_file","checksum":"270d2340402729b0532f7072ea914cae","file_size":13364601,"creator":"dernst","file_name":"2024_GeoscientificModelDev_Schmidt.pdf","success":1,"file_id":"15111"}],"publication":"Geoscientific Model Development","researchdata_availability":"yes","abstract":[{"text":"Global storm-resolving models (GSRMs) use strongly refined horizontal grids compared with the climate models typically used in the Coupled Model Intercomparison Project (CMIP) but employ comparable vertical grid spacings. Here, we study how changes in the vertical grid spacing and adjustments to the integration time step affect the basic climate quantities simulated by the ICON-Sapphire atmospheric GSRM. Simulations are performed over a 45 d period for five different vertical grids with between 55 and 540 vertical layers and maximum tropospheric vertical grid spacings of between 800 and 50 m, respectively. The effects of changes in the vertical grid spacing are compared with the effects of reducing the horizontal grid spacing from 5 to 2.5 km. For most of the quantities considered, halving the vertical grid spacing has a smaller effect than halving the horizontal grid spacing, but it is not negligible. Each halving of the vertical grid spacing, along with the necessary reductions in time step length, increases cloud liquid water by about 7 %, compared with an approximate 16 % decrease for halving the horizontal grid spacing. The effect is due to both the vertical grid refinement and the time step reduction. There is no tendency toward convergence in the range of grid spacings tested here. The cloud ice amount also increases with a refinement in the vertical grid, but it is hardly affected by the time step length and does show a tendency to converge. While the effect on shortwave radiation is globally dominated by the altered reflection due to the change in the cloud liquid water content, the effect on longwave radiation is more difficult to interpret because changes in the cloud ice concentration and cloud fraction are anticorrelated in some regions. The simulations show that using a maximum tropospheric vertical grid spacing larger than 400 m would increase the truncation error strongly. Computing time investments in a further vertical grid refinement can affect the truncation errors of GSRMs similarly to comparable investments in horizontal refinement, because halving the vertical grid spacing is generally cheaper than halving the horizontal grid spacing. However, convergence of boundary layer cloud properties cannot be expected, even for the smallest maximum tropospheric grid spacing of 50 m used in this study.","lang":"eng"}],"article_type":"original","quality_controlled":"1","article_processing_charge":"Yes (via OA deal)","dataavailabilitystatement":"Simulations were run with the ICON branch nextgems_cycle1_zstar_avr of the icon-aes repository as commit 2d18086d538ca6b80785f21b7a14808fbf50546c. This source code and run scripts are available from https://doi.org/10.17617/3.Z10MPA (Schmidt, 2023). The ICON model is available to licensed individuals (https://code.mpimet.mpg.de/projects/iconpublic/wiki/How to obtain the model code, last access: 10 July 2023). By downloading the ICON source code, the user accepts the license agreement. Scripts employed to produce the figures can be found at https://hdl.handle.net/21.11116/0000-000D-605D-F (last access: 15 December 2023). Radiosonde data are available from https://doi.org/10.5281/zenodo.7051674 (Schulz et al., 2022). CERES data are available from https://doi.org/10.5067/TERRA-AQUA-NOAA20/CERES/EBAF_L3B004.2 (NASA/LARC/SD/ASDC, 2023).","type":"journal_article","fulldoi":"https://doi.org/10.5194/gmd-17-1563-2024","publisher":"European Geosciences Union","tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","image":"/images/cc_by.png","short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"scopus_import":"1","oa_version":"Published Version","publication_status":"published","volume":17,"page":"1563-1584"},{"APC_amount":"2940 EUR","status":"public","department":[{"_id":"CaMu"}],"date_created":"2024-03-25T10:27:30Z","citation":{"chicago":"Hwong, Yi-Ling, and Caroline J Muller. “The Unreasonable Efficiency of Total Rain Evaporation Removal in Triggering Convective Self‐aggregation.” <i>Geophysical Research Letters</i>. Wiley, 2024. <a href=\"https://doi.org/10.1029/2023gl106523\">https://doi.org/10.1029/2023gl106523</a>.","ista":"Hwong Y-L, Muller CJ. 2024. The unreasonable efficiency of total rain evaporation removal in triggering convective self‐aggregation. Geophysical Research Letters. 51(6), e2023GL106523.","ieee":"Y.-L. Hwong and C. J. Muller, “The unreasonable efficiency of total rain evaporation removal in triggering convective self‐aggregation,” <i>Geophysical Research Letters</i>, vol. 51, no. 6. Wiley, 2024.","ama":"Hwong Y-L, Muller CJ. The unreasonable efficiency of total rain evaporation removal in triggering convective self‐aggregation. <i>Geophysical Research Letters</i>. 2024;51(6). doi:<a href=\"https://doi.org/10.1029/2023gl106523\">10.1029/2023gl106523</a>","apa":"Hwong, Y.-L., &#38; Muller, C. J. (2024). The unreasonable efficiency of total rain evaporation removal in triggering convective self‐aggregation. <i>Geophysical Research Letters</i>. Wiley. <a href=\"https://doi.org/10.1029/2023gl106523\">https://doi.org/10.1029/2023gl106523</a>","short":"Y.-L. Hwong, C.J. Muller, Geophysical Research Letters 51 (2024).","mla":"Hwong, Yi-Ling, and Caroline J. Muller. “The Unreasonable Efficiency of Total Rain Evaporation Removal in Triggering Convective Self‐aggregation.” <i>Geophysical Research Letters</i>, vol. 51, no. 6, e2023GL106523, Wiley, 2024, doi:<a href=\"https://doi.org/10.1029/2023gl106523\">10.1029/2023gl106523</a>."},"OA_type":"gold","year":"2024","month":"03","external_id":{"isi":["001187002300001"]},"author":[{"full_name":"Hwong, Yi-Ling","orcid":"0000-0001-9281-3479","first_name":"Yi-Ling","last_name":"Hwong","id":"1217aa61-4dd1-11ec-9ac3-f2ba3f17ee22"},{"first_name":"Caroline J","last_name":"Muller","id":"f978ccb0-3f7f-11eb-b193-b0e2bd13182b","orcid":"0000-0001-5836-5350","full_name":"Muller, Caroline J"}],"has_accepted_license":"1","oa":1,"file_date_updated":"2024-03-25T11:28:25Z","intvolume":"        51","supplementarymaterial":"yes","publication_identifier":{"eissn":["1944-8007"],"issn":["0094-8276"]},"OA_place":"publisher","das_tickbox":"1","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","date_published":"2024-03-19T00:00:00Z","ddc":["550"],"date_updated":"2026-10-01T09:22:29Z","keyword":["General Earth and Planetary Sciences","Geophysics"],"title":"The unreasonable efficiency of total rain evaporation removal in triggering convective self‐aggregation","day":"19","issue":"6","isi":1,"_id":"15186","language":[{"iso":"eng"}],"file":[{"date_updated":"2024-03-25T11:28:25Z","date_created":"2024-03-25T11:28:25Z","content_type":"application/pdf","access_level":"open_access","checksum":"eacb011091a503b9e7b748fef639ba4c","file_name":"2024_GeophysResLetters_Hwong.pdf","file_size":1280108,"creator":"dernst","success":1,"file_id":"15187","relation":"main_file"}],"acknowledgement":"YLH is supported by funding from the European Union's Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie Grant 101034413. CM gratefully acknowledges funding from the European Research Council (ERC) under the European Union's Horizon 2020 research and innovation program (Project CLUSTER, Grant 805041). The authors warmly thank Steven Sherwood, Jiawei Bao, Bidyut Goswami, and Martin Janssens for stimulating and helpful discussions. They also thank Christopher Holloway and an anonymous reviewer for providing helpful feedback that greatly improved this manuscript.\r\n","related_material":{"record":[{"id":"19307","relation":"research_data","status":"public"}]},"doi":"10.1029/2023gl106523","article_processing_charge":"Yes","quality_controlled":"1","abstract":[{"lang":"eng","text":"The elimination of rain evaporation in the planetary boundary layer (PBL) has been found to lead to convective self‐aggregation (CSA) even without radiative feedback, but the precise mechanisms underlying this phenomenon remain unclear. We conducted cloud‐resolving simulations with two domain sizes and progressively reduced rain evaporation in the PBL. Surprisingly, CSA only occurred when rain evaporation was almost completely removed. The additional convective heating resulting from the reduction of evaporative cooling in the moist patch was found to be the trigger, thereafter a dry subsidence intrusion into the PBL in the dry patch takes over and sets CSA in motion. Temperature and moisture anomalies oppose each other in their buoyancy effects, hence explaining the need for almost total rain evaporation removal. We also found radiative cooling and not cold pools to be the leading cause for the comparative ease of CSA to take place in the larger domain."}],"article_type":"original","publication":"Geophysical Research Letters","project":[{"call_identifier":"H2020","grant_number":"101034413","name":"IST-BRIDGE: International postdoctoral program","_id":"fc2ed2f7-9c52-11eb-aca3-c01059dda49c"},{"grant_number":"805041","name":"Organization of CLoUdS, and implications of Tropical  cyclones and for the Energetics of the tropics, in current and waRming climate","_id":"629205d8-2b32-11ec-9570-e1356ff73576","call_identifier":"H2020"}],"researchdata_availability":"yes","scopus_import":"1","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode","short":"CC BY-NC-ND (4.0)","name":"Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","image":"/images/cc_by_nc_nd.png"},"publisher":"Wiley","ec_funded":1,"fulldoi":"https://doi.org/10.1029/2023gl106523","DOAJ_listed":"1","type":"journal_article","dataavailabilitystatement":"The data, scripts and model source codes and files required to reproduce the results described in this manuscript are available in Hwong and Muller (2023)\r\nHwong, Y.-L., & Muller, C. (2023). Data - The unreasonable efficiency of total rain evaporation removal in triggering convective self-aggregation (version 5) [Dataset]. Zenodo. https://doi.org/10.5281/zenodo.10687169","article_number":" e2023GL106523","volume":51,"publication_status":"published","oa_version":"Published Version","corr_author":"1"},{"title":"A pre-monsoon signal of false alarms of Indian monsoon droughts","isi":1,"issue":"5","day":"16","_id":"15165","language":[{"iso":"eng"}],"supplementarymaterial":"yes","intvolume":"        51","publication_identifier":{"eissn":["1944-8007"],"issn":["0094-8276"]},"file_date_updated":"2024-03-25T08:36:00Z","das_tickbox":"1","OA_place":"publisher","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","date_published":"2024-03-16T00:00:00Z","date_updated":"2026-10-01T09:17:49Z","ddc":["550"],"month":"03","external_id":{"isi":["001181635700001"]},"author":[{"full_name":"Goswami, Bidyut B","orcid":"0000-0001-8602-3083","id":"3a4ac09c-6d61-11ec-bf66-884cde66b64b","last_name":"Goswami","first_name":"Bidyut B"}],"oa":1,"has_accepted_license":"1","APC_amount":"1470 EUR","status":"public","department":[{"_id":"CaMu"}],"year":"2024","OA_type":"gold","date_created":"2024-03-24T23:00:58Z","citation":{"chicago":"GOSWAMI, BIDYUT B. “A Pre-Monsoon Signal of False Alarms of Indian Monsoon Droughts.” <i>Geophysical Research Letters</i>. Wiley, 2024. <a href=\"https://doi.org/10.1029/2023GL106569\">https://doi.org/10.1029/2023GL106569</a>.","ista":"GOSWAMI BB. 2024. A pre-monsoon signal of false alarms of Indian monsoon droughts. Geophysical Research Letters. 51(5), e2023GL106569.","ieee":"B. B. GOSWAMI, “A pre-monsoon signal of false alarms of Indian monsoon droughts,” <i>Geophysical Research Letters</i>, vol. 51, no. 5. Wiley, 2024.","ama":"GOSWAMI BB. A pre-monsoon signal of false alarms of Indian monsoon droughts. <i>Geophysical Research Letters</i>. 2024;51(5). doi:<a href=\"https://doi.org/10.1029/2023GL106569\">10.1029/2023GL106569</a>","short":"B.B. GOSWAMI, Geophysical Research Letters 51 (2024).","apa":"GOSWAMI, B. B. (2024). A pre-monsoon signal of false alarms of Indian monsoon droughts. <i>Geophysical Research Letters</i>. Wiley. <a href=\"https://doi.org/10.1029/2023GL106569\">https://doi.org/10.1029/2023GL106569</a>","mla":"GOSWAMI, BIDYUT B. “A Pre-Monsoon Signal of False Alarms of Indian Monsoon Droughts.” <i>Geophysical Research Letters</i>, vol. 51, no. 5, e2023GL106569, Wiley, 2024, doi:<a href=\"https://doi.org/10.1029/2023GL106569\">10.1029/2023GL106569</a>."},"volume":51,"article_number":"e2023GL106569","oa_version":"Published Version","publication_status":"published","corr_author":"1","scopus_import":"1","publisher":"Wiley","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode","short":"CC BY-NC-ND (4.0)","name":"Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","image":"/images/cc_by_nc_nd.png"},"DOAJ_listed":"1","type":"journal_article","fulldoi":"https://doi.org/10.1029/2023GL106569","ec_funded":1,"dataavailabilitystatement":"The observed rainfall data analyzed in this study are from the IMD (Pai et al., 2015), and Tropical Rainfall Measurement Mission (TRMM) Multi-Satellite Precipitation Analysis (TMPA) 3B42 Version 7 product (Huffman et al., 2007), reanalysis data from 5th generation ECMWF reanalysis product (ERA5) (Hersbach et al., 2023), SST data from the HadISST1 data set provided by the Met Office Hadley Center (Rayner et al., 2003), available at https://www.metoffice.gov.uk/hadobs/hadisst/. The PDO index, computed following (Mantua et al., 1997; Zhang et al., 1997) using the UKMO Historical SST data set for 1900–81 (Parker et al., 1995); Reynold's Optimally Interpolated (OI) SST (V1) for January 1982–Dec 2001) (Reynolds et al., 2007) and OI SST Version 2 (V2) beginning January 2002–present, is obtained from the PDO web-page maintained by Dr. Nathan Mantua, NOAA Fisheries, available at http://research.jisao.washington.edu/pdo/PDO.latest.txt. The ENSO index, monthly NINO3.4 values, computed from HadISST1 data (Rayner et al., 2003), is obtained from the Global Climate Observing System (GCOS) Working Group on Surface Pressure (WG-SP), web-page hosted by NOAA Physical Sciences Laboratory (PSL), available at https://psl.noaa.gov/gcos_wgsp/Timeseries/Data/nino34.long.anom.data. The linear regression model, that we constructed, is based on the LinearRegression function from sklearn Python package; the python script for this regression analysis is available at (Goswami, 2023).","article_processing_charge":"Yes","quality_controlled":"1","abstract":[{"text":"Current knowledge suggests a drought Indian monsoon (perhaps a severe one) when the El Nino Southern Oscillation and Pacific Decadal Oscillation each exhibit positive phases (a joint positive phase). For the monsoons, which are exceptions in this regard, we found northeast India often gets excess pre-monsoon rainfall. Further investigation reveals that this excess pre-monsoon rainfall is produced by the interaction of the large-scale circulation associated with the joint phase with the mountains in northeast India. We posit that a warmer troposphere, a consequence of excess rainfall over northeast India, drives a stronger monsoon circulation and enhances monsoon rainfall over central India. Hence, we argue that pre-monsoon rainfall over northeast India can be used for seasonal monsoon rainfall prediction over central India. Most importantly, its predictive value is at its peak when the Pacific Ocean exhibits a joint positive phase and the threat of extreme drought monsoon looms over India.","lang":"eng"}],"article_type":"original","project":[{"name":"Organization of CLoUdS, and implications of Tropical  cyclones and for the Energetics of the tropics, in current and waRming climate","grant_number":"805041","_id":"629205d8-2b32-11ec-9570-e1356ff73576","call_identifier":"H2020"}],"researchdata_availability":"not applicable","publication":"Geophysical Research Letters","file":[{"relation":"main_file","checksum":"243bd966aca968ec7d9e474af8639f8d","file_name":"2024_GeophysResLetters_Goswami.pdf","creator":"dernst","file_size":2887134,"success":1,"file_id":"15178","content_type":"application/pdf","access_level":"open_access","date_created":"2024-03-25T08:36:00Z","date_updated":"2024-03-25T08:36:00Z"}],"acknowledgement":"The author gratefully acknowledges ISTA for supporting this research through funding from the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (Project CLUSTER, grant agreement No. 805041).","doi":"10.1029/2023GL106569"},{"article_processing_charge":"Yes","quality_controlled":"1","article_type":"original","abstract":[{"text":"This study investigates the response of Indian summer monsoon (ISM) precipitation to CO2 removal, with a specific focus on regional and subseasonal variations. Following CO2 removal, monsoon circulation weakens throughout the summer owing to the reduced large-scale meridional temperature gradient around India. Weakened monsoon circulation decreases the local-scale thermodynamic stability within India, following monsoon-onset periods. While the frequency of synoptic-scale ISM low-pressure systems (LPSs) decreases overall, the lower thermodynamic stability causes the LPSs to form and resultantly shift west and south from their typical paths, last longer and move more quickly zonally during August and September. Changes in these rain-producing processes induce distinct regional (Western Ghats, south-central-east India, and Tamil Nadu) and subseasonal precipitation responses. Also, extreme precipitation exhibits similar patterns, but is more strongly affected by changes in LPS. Our results suggest that reliable future projections of regional hydroclimate change require a more accurate understanding of multi-scale precipitation processes.","lang":"eng"}],"researchdata_availability":"upon request","publication":"npj Climate and Atmospheric Science","file":[{"relation":"main_file","file_id":"18717","success":1,"file_size":1927871,"creator":"dernst","checksum":"6b3148315a444835113c32b399010370","file_name":"2024_npjclimate_Paik.pdf","access_level":"open_access","content_type":"application/pdf","date_created":"2025-01-02T08:49:13Z","date_updated":"2025-01-02T08:49:13Z"}],"acknowledgement":"This study was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (NRF-2018R1A5A1024958, NRF-2021R1C1C2094185, RS-2024-00336160). Model simulation and data transfer were supported by the National Supercomputing Center with supercomputing resources including technical support (KSC-2021-CHA-0030), the National Center for Meteorological Supercomputer of the Korea Meteorological Administration (KMA), and by the Korea Research Environment Open NETwork (KREONET), respectively. DK was supported by New Faculty Startup Fund from Seoul National University. We acknowledge the World Climate Research Programme, which, through its Working Group on Coupled Modelling, coordinated and promoted CMIP6. We thank the climate modeling groups for producing and making available their model output, the Earth System Grid Federation (ESGF) for archiving the data and providing access (https://esgf-node.llnl.gov/projects/cmip6/), and the multiple funding agencies who support CMIP6 and ESGF.","doi":"10.1038/s41612-024-00858-0","volume":7,"article_number":"305","oa_version":"Published Version","publication_status":"published","scopus_import":"1","publisher":"Springer Nature","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode","short":"CC BY-NC-ND (4.0)","name":"Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","image":"/images/cc_by_nc_nd.png"},"DOAJ_listed":"1","type":"journal_article","fulldoi":"https://doi.org/10.1038/s41612-024-00858-0","dataavailabilitystatement":"CESM1 simulation datasets supporting the results will be provided upon a reasonable request. Global Precipitation Climatology Project version 2.3 can be accessed at https://www.ncei.noaa.gov/data/global-precipitation-climatology-project-gpcp-monthly/access/. ERA5 datasets can be accessed at https://doi.org/10.24381/cds.bd0915c6, https://doi.org/10.24381/cds.adbb2d47 and https://doi.org/10.24381/cds.6860a573. Global Precipitation Climatology Centre version 2022 can be accessed at https://opendata.dwd.de/climate_environment/GPCC/html/fulldata-monthly_v2022_doi_download.html. All of the CMIP6 model simulation datasets used in this study can be accessed at https://esgf-node.llnl.gov/search/cmip6/.","month":"12","external_id":{"isi":["001381218300007"]},"author":[{"first_name":"Seungmok","last_name":"Paik","full_name":"Paik, Seungmok"},{"first_name":"Daehyun","last_name":"Kim","full_name":"Kim, Daehyun"},{"first_name":"Soon Il","last_name":"An","full_name":"An, Soon Il"},{"full_name":"Oh, Hyoeun","first_name":"Hyoeun","last_name":"Oh"},{"first_name":"Jongsoo","last_name":"Shin","full_name":"Shin, Jongsoo"},{"full_name":"Goswami, Bidyut B","orcid":"0000-0001-8602-3083","first_name":"Bidyut B","id":"3a4ac09c-6d61-11ec-bf66-884cde66b64b","last_name":"Goswami"},{"first_name":"Seung Ki","last_name":"Min","full_name":"Min, Seung Ki"},{"last_name":"Mondal","first_name":"Sanjit Kumar","full_name":"Mondal, Sanjit Kumar"}],"has_accepted_license":"1","oa":1,"status":"public","department":[{"_id":"CaMu"}],"year":"2024","OA_type":"gold","citation":{"apa":"Paik, S., Kim, D., An, S. I., Oh, H., Shin, J., GOSWAMI, B. B., … Mondal, S. K. (2024). Exploring causes of distinct regional and subseasonal Indian summer monsoon precipitation responses to CO2 removal. <i>Npj Climate and Atmospheric Science</i>. Springer Nature. <a href=\"https://doi.org/10.1038/s41612-024-00858-0\">https://doi.org/10.1038/s41612-024-00858-0</a>","short":"S. Paik, D. Kim, S.I. An, H. Oh, J. Shin, B.B. GOSWAMI, S.K. Min, S.K. Mondal, Npj Climate and Atmospheric Science 7 (2024).","ama":"Paik S, Kim D, An SI, et al. Exploring causes of distinct regional and subseasonal Indian summer monsoon precipitation responses to CO2 removal. <i>npj Climate and Atmospheric Science</i>. 2024;7. doi:<a href=\"https://doi.org/10.1038/s41612-024-00858-0\">10.1038/s41612-024-00858-0</a>","mla":"Paik, Seungmok, et al. “Exploring Causes of Distinct Regional and Subseasonal Indian Summer Monsoon Precipitation Responses to CO2 Removal.” <i>Npj Climate and Atmospheric Science</i>, vol. 7, 305, Springer Nature, 2024, doi:<a href=\"https://doi.org/10.1038/s41612-024-00858-0\">10.1038/s41612-024-00858-0</a>.","ieee":"S. Paik <i>et al.</i>, “Exploring causes of distinct regional and subseasonal Indian summer monsoon precipitation responses to CO2 removal,” <i>npj Climate and Atmospheric Science</i>, vol. 7. Springer Nature, 2024.","ista":"Paik S, Kim D, An SI, Oh H, Shin J, GOSWAMI BB, Min SK, Mondal SK. 2024. Exploring causes of distinct regional and subseasonal Indian summer monsoon precipitation responses to CO2 removal. npj Climate and Atmospheric Science. 7, 305.","chicago":"Paik, Seungmok, Daehyun Kim, Soon Il An, Hyoeun Oh, Jongsoo Shin, BIDYUT B GOSWAMI, Seung Ki Min, and Sanjit Kumar Mondal. “Exploring Causes of Distinct Regional and Subseasonal Indian Summer Monsoon Precipitation Responses to CO2 Removal.” <i>Npj Climate and Atmospheric Science</i>. Springer Nature, 2024. <a href=\"https://doi.org/10.1038/s41612-024-00858-0\">https://doi.org/10.1038/s41612-024-00858-0</a>."},"date_created":"2024-12-29T23:01:57Z","title":"Exploring causes of distinct regional and subseasonal Indian summer monsoon precipitation responses to CO2 removal","isi":1,"day":"19","language":[{"iso":"eng"}],"_id":"18708","publication_identifier":{"eissn":["2397-3722"]},"intvolume":"         7","supplementarymaterial":"yes","file_date_updated":"2025-01-02T08:49:13Z","das_tickbox":"1","OA_place":"publisher","ddc":["550"],"date_published":"2024-12-19T00:00:00Z","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","date_updated":"2026-10-01T09:26:16Z"},{"article_processing_charge":"No","month":"02","has_accepted_license":"1","oa":1,"author":[{"first_name":"Yi-Ling","last_name":"Hwong","id":"1217aa61-4dd1-11ec-9ac3-f2ba3f17ee22","orcid":"0000-0001-9281-3479","full_name":"Hwong, Yi-Ling"},{"full_name":"Muller, Caroline J","orcid":"0000-0001-5836-5350","last_name":"Muller","id":"f978ccb0-3f7f-11eb-b193-b0e2bd13182b","first_name":"Caroline J"}],"abstract":[{"text":"This repository contains the data, scripts, SAM codes and files required to reproduce the results of the manuscript \"The Unreasonable Efficiency of Total Rain Evaporation Removal in Triggering Convective Self-Aggregation\" submitted to the Geophysical Research Letters (GRL).\r\n\r\nBrief description of project: This project aims to examine the impact of rain evaporation removal or reduction in the planetary boundary layer (PBL) on convective self aggregation (CSA). Non-rotating radiative-convective equilibrium (RCE) simulations were conducted with the System for Atmospheric Modeling (SAM) cloud resolving model. Rain evaporation in the lowest 1 km was progressively reduced and the effect on CSA was investigated. The physical processes underlying this type of aggregation (referred to in the manuscript as no-evaporation CSA, or NE-CSA) were analyzed and described. \r\nThe default SAM code base (version 6.10.8) can be downloaded from here: http://rossby.msrc.sunysb.edu/~marat/SAM.html","lang":"eng"}],"status":"public","date_created":"2025-03-07T08:39:40Z","doi":"10.5281/ZENODO.10687169","citation":{"ama":"Hwong Y-L, Muller CJ. Data - The unreasonable efficiency of total rain evaporation removal in triggering convective self-aggregation. 2024. doi:<a href=\"https://doi.org/10.5281/ZENODO.10687169\">10.5281/ZENODO.10687169</a>","apa":"Hwong, Y.-L., &#38; Muller, C. J. (2024). Data - The unreasonable efficiency of total rain evaporation removal in triggering convective self-aggregation. Zenodo. <a href=\"https://doi.org/10.5281/ZENODO.10687169\">https://doi.org/10.5281/ZENODO.10687169</a>","short":"Y.-L. Hwong, C.J. Muller, (2024).","mla":"Hwong, Yi-Ling, and Caroline J. Muller. <i>Data - The Unreasonable Efficiency of Total Rain Evaporation Removal in Triggering Convective Self-Aggregation</i>. Zenodo, 2024, doi:<a href=\"https://doi.org/10.5281/ZENODO.10687169\">10.5281/ZENODO.10687169</a>.","ista":"Hwong Y-L, Muller CJ. 2024. Data - The unreasonable efficiency of total rain evaporation removal in triggering convective self-aggregation, Zenodo, <a href=\"https://doi.org/10.5281/ZENODO.10687169\">10.5281/ZENODO.10687169</a>.","chicago":"Hwong, Yi-Ling, and Caroline J Muller. “Data - The Unreasonable Efficiency of Total Rain Evaporation Removal in Triggering Convective Self-Aggregation.” Zenodo, 2024. <a href=\"https://doi.org/10.5281/ZENODO.10687169\">https://doi.org/10.5281/ZENODO.10687169</a>.","ieee":"Y.-L. Hwong and C. J. Muller, “Data - The unreasonable efficiency of total rain evaporation removal in triggering convective self-aggregation.” Zenodo, 2024."},"OA_type":"green","year":"2024","related_material":{"record":[{"id":"15186","relation":"used_in_publication","status":"public"}]},"department":[{"_id":"CaMu"}],"title":"Data - The unreasonable efficiency of total rain evaporation removal in triggering convective self-aggregation","_id":"19307","corr_author":"1","day":"21","oa_version":"Published Version","tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","image":"/images/cc_by.png","short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"publisher":"Zenodo","OA_place":"repository","main_file_link":[{"url":"https://doi.org/10.5281/zenodo.8369509","open_access":"1"}],"ddc":["550"],"date_updated":"2026-10-01T09:22:28Z","date_published":"2024-02-21T00:00:00Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","fulldoi":"https://doi.org/10.5281/ZENODO.10687169","type":"research_data_reference"},{"file_date_updated":"2024-07-17T09:29:13Z","supplementarymaterial":"yes","publication_identifier":{"issn":["0730-0301"],"eissn":["1557-7368"]},"intvolume":"        43","das_tickbox":"0","ddc":["516"],"user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","date_updated":"2026-10-01T09:30:01Z","date_published":"2024-07-01T00:00:00Z","keyword":["Topology Optimization","Mass Moments","Computational Geometry"],"title":"Spin-it faster: Quadrics solve all topology optimization problems that depend only on mass moments","day":"01","issue":"4","isi":1,"language":[{"iso":"eng"}],"_id":"17203","status":"public","department":[{"_id":"ChWo"}],"date_created":"2024-07-05T12:08:57Z","citation":{"chicago":"Hafner, Christian, Mickaël Ly, and Chris Wojtan. “Spin-It Faster: Quadrics Solve All Topology Optimization Problems That Depend Only on Mass Moments.” <i>Transactions on Graphics</i>. Association for Computing Machinery, 2024. <a href=\"https://doi.org/10.1145/3658194\">https://doi.org/10.1145/3658194</a>.","ista":"Hafner C, Ly M, Wojtan C. 2024. Spin-it faster: Quadrics solve all topology optimization problems that depend only on mass moments. Transactions on Graphics. 43(4), 78.","ieee":"C. Hafner, M. Ly, and C. Wojtan, “Spin-it faster: Quadrics solve all topology optimization problems that depend only on mass moments,” <i>Transactions on Graphics</i>, vol. 43, no. 4. Association for Computing Machinery, 2024.","mla":"Hafner, Christian, et al. “Spin-It Faster: Quadrics Solve All Topology Optimization Problems That Depend Only on Mass Moments.” <i>Transactions on Graphics</i>, vol. 43, no. 4, 78, Association for Computing Machinery, 2024, doi:<a href=\"https://doi.org/10.1145/3658194\">10.1145/3658194</a>.","ama":"Hafner C, Ly M, Wojtan C. Spin-it faster: Quadrics solve all topology optimization problems that depend only on mass moments. <i>Transactions on Graphics</i>. 2024;43(4). doi:<a href=\"https://doi.org/10.1145/3658194\">10.1145/3658194</a>","short":"C. Hafner, M. Ly, C. Wojtan, Transactions on Graphics 43 (2024).","apa":"Hafner, C., Ly, M., &#38; Wojtan, C. (2024). Spin-it faster: Quadrics solve all topology optimization problems that depend only on mass moments. <i>Transactions on Graphics</i>. Denver, Colorado: Association for Computing Machinery. <a href=\"https://doi.org/10.1145/3658194\">https://doi.org/10.1145/3658194</a>"},"year":"2024","month":"07","external_id":{"isi":["001289270900045"]},"conference":{"start_date":"2024-07-28","end_date":"2024-08-01","location":"Denver, Colorado"},"author":[{"full_name":"Hafner, Christian","first_name":"Christian","last_name":"Hafner","id":"400429CC-F248-11E8-B48F-1D18A9856A87"},{"first_name":"Mickaël","last_name":"Ly","id":"6340d7f0-b48d-11eb-b10d-b7487e71d9f1","full_name":"Ly, Mickaël"},{"orcid":"0000-0001-6646-5546","full_name":"Wojtan, Christopher J","last_name":"Wojtan","id":"3C61F1D2-F248-11E8-B48F-1D18A9856A87","first_name":"Christopher J"}],"oa":1,"has_accepted_license":"1","scopus_import":"1","publisher":"Association for Computing Machinery","fulldoi":"https://doi.org/10.1145/3658194","type":"journal_article","article_number":"78","volume":43,"publication_status":"published","oa_version":"Published Version","corr_author":"1","file":[{"relation":"main_file","file_size":7225150,"file_name":"sif-final.pdf","checksum":"0dc9f5a6422b8a49a79026900f349ee5","creator":"chafner","file_id":"17204","success":1,"content_type":"application/pdf","access_level":"open_access","date_created":"2024-07-05T12:05:17Z","date_updated":"2024-07-05T12:05:17Z"},{"content_type":"application/pdf","access_level":"open_access","date_created":"2024-07-05T12:06:03Z","date_updated":"2024-07-05T12:06:03Z","relation":"supplementary_material","file_name":"sif-supp-final.pdf","checksum":"cde433c6a40688d5f1187fb5721f6f94","file_size":397262,"creator":"chafner","file_id":"17205"},{"access_level":"open_access","content_type":"video/mp4","date_updated":"2024-07-17T09:29:13Z","date_created":"2024-07-17T09:29:13Z","title":"Submission Video","relation":"supplementary_material","file_id":"17276","checksum":"c0457a09c2ab9a1c2935c995dcc84907","file_name":"sif-video-final.mp4","file_size":170001305,"creator":"chafner"}],"acknowledgement":"We thank Gianmarco Cherchi for his help in tailoring the Mesh Booleans code for this project, Stefan Jeschke for his help with the photographs, Malina Strugaru and Aleksei Kalinov for their help with the samples, and the anonymous reviewers as well as the members of the ISTA Visual Computing Group for their feedback. This project was funded in part by the European Research Council (ERC Consolidator Grant 101045083 CoDiNA).","doi":"10.1145/3658194","article_processing_charge":"Yes (via OA deal)","quality_controlled":"1","abstract":[{"text":"The behavior of a rigid body primarily depends on its mass moments, which consist of the mass, center of mass, and moments of inertia. It is possible to manipulate these quantities without altering the geometric appearance of an object by introducing cavities in its interior. Algorithms that find cavities of suitable shapes and sizes have enabled the computational design of spinning tops, yo-yos, wheels, buoys, and statically balanced objects. Previous work is based, for example, on topology optimization on voxel grids, which introduces a large number of optimization variables and box constraints, or offset surface computation, which cannot guarantee that solutions to a feasible problem will always be found.\r\n\r\nIn this work, we provide a mathematical analysis of constrained topology optimization problems that depend only on mass moments. This class of problems covers, among others, all applications mentioned above. Our main result is to show that no matter the outer shape of the rigid body to be optimized or the optimization objective and constraints considered, the optimal solution always features a quadric-shaped interface between material and cavities. This proves that optimal interfaces are always ellipsoids, hyperboloids, paraboloids, or one of a few degenerate cases, such as planes.\r\n\r\nThis insight lets us replace a difficult topology optimization problem with a provably equivalent non-linear equation system in a small number (<10) of variables, which represent the coefficients of the quadric. This system can be solved in a few seconds for most examples, provides insights into the geometric structure of many specific applications, and lets us describe their solution properties. Finally, our method integrates seamlessly into modern fabrication workflows because our solutions are analytical surfaces that are native to the CAD domain.","lang":"eng"}],"article_type":"original","publication":"Transactions on Graphics","project":[{"grant_number":"101045083","name":"Computational Discovery of Numerical Algorithms for Animation and Simulation of Natural Phenomena","_id":"34bc2376-11ca-11ed-8bc3-9a3b3961a088"}],"researchdata_availability":"no"},{"corr_author":"1","publication_status":"published","oa_version":"Published Version","article_number":"108011","volume":134,"acknowledged_ssus":[{"_id":"ScienComp"}],"dataavailabilitystatement":"Data will be made available on request","ec_funded":1,"fulldoi":"https://doi.org/10.1016/j.cnsns.2024.108011","type":"journal_article","tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","image":"/images/cc_by.png","short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"publisher":"Elsevier","scopus_import":"1","project":[{"name":"IST-BRIDGE: International postdoctoral program","grant_number":"101034413","_id":"fc2ed2f7-9c52-11eb-aca3-c01059dda49c","call_identifier":"H2020"},{"_id":"629205d8-2b32-11ec-9570-e1356ff73576","grant_number":"805041","name":"Organization of CLoUdS, and implications of Tropical  cyclones and for the Energetics of the tropics, in current and waRming climate","call_identifier":"H2020"}],"researchdata_availability":"upon request","publication":"Communications in Nonlinear Science and Numerical Simulation","article_type":"original","abstract":[{"lang":"eng","text":"Our goal is to investigate fundamental properties of the system of internally cooled convection. The system consists of an upward thermal flux at the lower boundary, a mean temperature lapse-rate and a constant cooling term in the bulk with the bulk cooling in thermal equilibrium with the input heat flux. This simple model represents idealised dry convection in the atmospheric boundary layer, where the cooling mimics the radiative cooling to space notably through longwave radiation. We perform linear stability analysis of the model for different values of the mean stratification to derive the critical forcing above which the fluid is convectively unstable to small perturbations. The dynamic behavior of the fluid system is described and the scaling of various important measured quantities such as the total vertical convective heat flux and the upward mass flux is measured. We introduce a lapse-rate dependent dimensionless Rayleigh-number Ray that determines the behavior of the system, finding that the convective heat-flux and mass-flux scale approximately as Ray0.5 and Ray0.7 respectively. The area-fraction of the domain that is occupied by upward and downward moving fluid and the skewness of the vertical velocity are studied to understand the asymmetry inherent in the system. We conclude with a short discussion on the relevance to atmospheric convection and the scope for further investigations of atmospheric convection using similar simplified approaches."}],"quality_controlled":"1","article_processing_charge":"Yes (via OA deal)","doi":"10.1016/j.cnsns.2024.108011","acknowledgement":"This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska–Curie grant agreement No. 101034413. CM gratefully acknowledges funding from the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation program (Project CLUSTER, Grant Agreement No. 805041). This research was supported by the Scientific Service Units (SSU) of IST Austria through resources provided by Scientific Computing (SciComp).","file":[{"access_level":"open_access","content_type":"application/pdf","date_created":"2025-01-09T09:05:31Z","date_updated":"2025-01-09T09:05:31Z","relation":"main_file","file_id":"18795","success":1,"file_size":1257925,"file_name":"2024_CommNonlinear_Agasthya.pdf","checksum":"9b7c2b8281d0b7bc7f08e0468168324c","creator":"dernst"}],"_id":"15313","language":[{"iso":"eng"}],"day":"01","isi":1,"title":"Dynamics and scaling of internally cooled convection","arxiv":1,"user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","ddc":["550"],"date_updated":"2026-10-01T09:27:13Z","date_published":"2024-07-01T00:00:00Z","das_tickbox":"1","OA_place":"publisher","file_date_updated":"2025-01-09T09:05:31Z","supplementarymaterial":"no","intvolume":"       134","publication_identifier":{"issn":["1007-5704"]},"has_accepted_license":"1","oa":1,"author":[{"full_name":"Agasthya, Lokahith N","last_name":"Agasthya","id":"cd100965-0804-11ed-9c55-f4878ff4e877","first_name":"Lokahith N"},{"full_name":"Muller, Caroline J","orcid":"0000-0001-5836-5350","id":"f978ccb0-3f7f-11eb-b193-b0e2bd13182b","last_name":"Muller","first_name":"Caroline J"}],"external_id":{"isi":["001238294600001"],"arxiv":["2311.04114"]},"month":"07","citation":{"ieee":"L. N. Agasthya and C. J. Muller, “Dynamics and scaling of internally cooled convection,” <i>Communications in Nonlinear Science and Numerical Simulation</i>, vol. 134. Elsevier, 2024.","chicago":"Agasthya, Lokahith N, and Caroline J Muller. “Dynamics and Scaling of Internally Cooled Convection.” <i>Communications in Nonlinear Science and Numerical Simulation</i>. Elsevier, 2024. <a href=\"https://doi.org/10.1016/j.cnsns.2024.108011\">https://doi.org/10.1016/j.cnsns.2024.108011</a>.","ista":"Agasthya LN, Muller CJ. 2024. Dynamics and scaling of internally cooled convection. Communications in Nonlinear Science and Numerical Simulation. 134, 108011.","mla":"Agasthya, Lokahith N., and Caroline J. Muller. “Dynamics and Scaling of Internally Cooled Convection.” <i>Communications in Nonlinear Science and Numerical Simulation</i>, vol. 134, 108011, Elsevier, 2024, doi:<a href=\"https://doi.org/10.1016/j.cnsns.2024.108011\">10.1016/j.cnsns.2024.108011</a>.","short":"L.N. Agasthya, C.J. Muller, Communications in Nonlinear Science and Numerical Simulation 134 (2024).","apa":"Agasthya, L. N., &#38; Muller, C. J. (2024). Dynamics and scaling of internally cooled convection. <i>Communications in Nonlinear Science and Numerical Simulation</i>. Elsevier. <a href=\"https://doi.org/10.1016/j.cnsns.2024.108011\">https://doi.org/10.1016/j.cnsns.2024.108011</a>","ama":"Agasthya LN, Muller CJ. Dynamics and scaling of internally cooled convection. <i>Communications in Nonlinear Science and Numerical Simulation</i>. 2024;134. doi:<a href=\"https://doi.org/10.1016/j.cnsns.2024.108011\">10.1016/j.cnsns.2024.108011</a>"},"date_created":"2024-04-14T22:01:01Z","year":"2024","OA_type":"hybrid","department":[{"_id":"CaMu"}],"status":"public"},{"author":[{"id":"e499926b-f6e0-11ea-865d-9c63db0031e8","last_name":"Scott","first_name":"Jonathan A","full_name":"Scott, Jonathan A"},{"full_name":"Zakerinia, Hossein","orcid":"0009-0007-3977-6462","first_name":"Hossein","id":"653bd8b6-f394-11eb-9cf6-c0bbf6cd78d4","last_name":"Zakerinia"},{"full_name":"Lampert, Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","first_name":"Christoph"}],"conference":{"start_date":"2024-03-07","location":"Vienna, Austria","name":"ICLR: International Conference on Learning Representations","end_date":"2024-03-07"},"has_accepted_license":"1","oa":1,"month":"03","external_id":{"arxiv":["2306.05515"]},"department":[{"_id":"ChLa"}],"year":"2024","citation":{"mla":"Scott, Jonathan A., et al. “PEFLL: Personalized Federated Learning by Learning to Learn.” <i>12th International Conference on Learning Representations</i>, OpenReview, 2024.","ama":"Scott JA, Zakerinia H, Lampert C. PEFLL: Personalized federated learning by learning to learn. In: <i>12th International Conference on Learning Representations</i>. OpenReview; 2024.","apa":"Scott, J. A., Zakerinia, H., &#38; Lampert, C. (2024). PEFLL: Personalized federated learning by learning to learn. In <i>12th International Conference on Learning Representations</i>. Vienna, Austria: OpenReview.","short":"J.A. Scott, H. Zakerinia, C. Lampert, in:, 12th International Conference on Learning Representations, OpenReview, 2024.","ista":"Scott JA, Zakerinia H, Lampert C. 2024. PEFLL: Personalized federated learning by learning to learn. 12th International Conference on Learning Representations. ICLR: International Conference on Learning Representations.","chicago":"Scott, Jonathan A, Hossein Zakerinia, and Christoph Lampert. “PEFLL: Personalized Federated Learning by Learning to Learn.” In <i>12th International Conference on Learning Representations</i>. OpenReview, 2024.","ieee":"J. A. Scott, H. Zakerinia, and C. Lampert, “PEFLL: Personalized federated learning by learning to learn,” in <i>12th International Conference on Learning Representations</i>, Vienna, Austria, 2024."},"date_created":"2024-08-11T22:01:12Z","status":"public","day":"07","language":[{"iso":"eng"}],"_id":"17411","arxiv":1,"title":"PEFLL: Personalized federated learning by learning to learn","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","date_published":"2024-03-07T00:00:00Z","date_updated":"2026-10-01T09:28:03Z","ddc":["000"],"supplementarymaterial":"no","file_date_updated":"2024-08-12T07:38:06Z","das_tickbox":"0","abstract":[{"text":"We present PeFLL, a new personalized federated learning algorithm that improves\r\nover the state-of-the-art in three aspects: 1) it produces more accurate models,\r\nespecially in the low-data regime, and not only for clients present during its\r\ntraining phase, but also for any that may emerge in the future; 2) it reduces the\r\namount of on-client computation and client-server communication by providing\r\nfuture clients with ready-to-use personalized models that require no additional\r\nfinetuning or optimization; 3) it comes with theoretical guarantees that establish\r\ngeneralization from the observed clients to future ones.\r\nAt the core of PeFLL lies a learning-to-learn approach that jointly trains an\r\nembedding network and a hypernetwork. The embedding network is used to\r\nrepresent clients in a latent descriptor space in a way that reflects their similarity\r\nto each other. The hypernetwork takes as input such descriptors and outputs the\r\nparameters of fully personalized client models. In combination, both networks\r\nconstitute a learning algorithm that achieves state-of-the-art performance in several\r\npersonalized federated learning benchmarks","lang":"eng"}],"researchdata_availability":"no","publication":"12th International Conference on Learning Representations","article_processing_charge":"No","quality_controlled":"1","related_material":{"record":[{"id":"21198","relation":"dissertation_contains","status":"public"}]},"acknowledgement":"This research was supported by the Scientific Service Units (SSU) of ISTA through resources provided by Scientific Computing (SciComp).\r\n","file":[{"access_level":"open_access","content_type":"application/pdf","date_updated":"2024-08-12T07:38:06Z","date_created":"2024-08-12T07:38:06Z","relation":"main_file","success":1,"file_id":"17415","file_name":"2024_ICLR_Scott.pdf","creator":"dernst","checksum":"81b7ea2e667adaf9c7a7b6b376b1f251","file_size":1029219}],"oa_version":"Published Version","publication_status":"published","corr_author":"1","acknowledged_ssus":[{"_id":"ScienComp"}],"type":"conference","scopus_import":"1","publisher":"OpenReview"},{"oa_version":"Preprint","publication_status":"published","corr_author":"1","volume":235,"alternative_title":["PMLR"],"page":"44012-44037","type":"conference","scopus_import":"1","main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2406.02416"}],"publisher":"ML Research Press","abstract":[{"text":"In practice, training using federated learning can be orders of magnitude slower than standard centralized training. This severely limits the amount of experimentation and tuning that can be done, making it challenging to obtain good performance on a given task. Server-side proxy data can be used to run training simulations, for instance for hyperparameter tuning. This can greatly speed up the training pipeline by reducing the number of tuning runs to be performed overall on the true clients. However, it is challenging to ensure that these simulations accurately reflect the dynamics of the real federated training. In particular, the proxy data used for simulations often comes as a single centralized dataset without a partition into distinct clients, and partitioning this data in a naive way can lead to simulations that poorly reflect real federated training. In this paper we address the challenge of how to partition centralized data in a way that reflects the statistical heterogeneity of the true federated clients. We propose a fully federated, theoretically justified, algorithm that efficiently learns the distribution of the true clients and observe improved server-side simulations when using the inferred distribution to create simulated clients from the centralized data.","lang":"eng"}],"publication":"Proceedings of the 41st International Conference on Machine Learning","researchdata_availability":"no","article_processing_charge":"No","quality_controlled":"1","related_material":{"record":[{"id":"21198","status":"public","relation":"dissertation_contains"}]},"acknowledgement":"We would like to thank: Mona Chitnis and everyone in the Private Federated Learning team at Apple for their help and support throughout the entire project; Audra McMillan, Martin Pelikan, Anosh Raj and Barry Theobold for feedback on the initial versions of the paper; and Christoph Lampert for valuable feedback on the paper structure and suggestions for additional experiments.","day":"01","_id":"18120","language":[{"iso":"eng"}],"arxiv":1,"title":"Improved modelling of federated datasets using mixtures-of-Dirichlet-multinomials","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","date_published":"2024-09-01T00:00:00Z","date_updated":"2026-10-01T09:29:04Z","supplementarymaterial":"no","publication_identifier":{"eissn":["2640-3498"]},"intvolume":"       235","das_tickbox":"0","author":[{"id":"e499926b-f6e0-11ea-865d-9c63db0031e8","last_name":"Scott","first_name":"Jonathan A","full_name":"Scott, Jonathan A"},{"full_name":"Cahill, Áine","last_name":"Cahill","first_name":"Áine"}],"conference":{"start_date":"2024-07-21","location":"Vienna, Austria","name":"ICML: International Conference on Machine Learning","end_date":"2024-07-27"},"oa":1,"month":"09","external_id":{"arxiv":["2406.02416"]},"department":[{"_id":"ChLa"}],"year":"2024","citation":{"apa":"Scott, J. A., &#38; Cahill, Á. (2024). Improved modelling of federated datasets using mixtures-of-Dirichlet-multinomials. In <i>Proceedings of the 41st International Conference on Machine Learning</i> (Vol. 235, pp. 44012–44037). Vienna, Austria: ML Research Press.","short":"J.A. Scott, Á. Cahill, in:, Proceedings of the 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 44012–44037.","ama":"Scott JA, Cahill Á. Improved modelling of federated datasets using mixtures-of-Dirichlet-multinomials. In: <i>Proceedings of the 41st International Conference on Machine Learning</i>. Vol 235. ML Research Press; 2024:44012-44037.","mla":"Scott, Jonathan A., and Áine Cahill. “Improved Modelling of Federated Datasets Using Mixtures-of-Dirichlet-Multinomials.” <i>Proceedings of the 41st International Conference on Machine Learning</i>, vol. 235, ML Research Press, 2024, pp. 44012–37.","ieee":"J. A. Scott and Á. Cahill, “Improved modelling of federated datasets using mixtures-of-Dirichlet-multinomials,” in <i>Proceedings of the 41st International Conference on Machine Learning</i>, Vienna, Austria, 2024, vol. 235, pp. 44012–44037.","chicago":"Scott, Jonathan A, and Áine Cahill. “Improved Modelling of Federated Datasets Using Mixtures-of-Dirichlet-Multinomials.” In <i>Proceedings of the 41st International Conference on Machine Learning</i>, 235:44012–37. ML Research Press, 2024.","ista":"Scott JA, Cahill Á. 2024. Improved modelling of federated datasets using mixtures-of-Dirichlet-multinomials. Proceedings of the 41st International Conference on Machine Learning. ICML: International Conference on Machine Learning, PMLR, vol. 235, 44012–44037."},"date_created":"2024-09-22T22:01:45Z","status":"public"},{"publisher":"ML Research Press","scopus_import":"1","main_file_link":[{"open_access":"1","url":" https://doi.org/10.48550/arXiv.2402.04054"}],"type":"conference","page":"58122-58139","alternative_title":["PMLR"],"volume":235,"corr_author":"1","publication_status":"published","oa_version":"Published Version","quality_controlled":"1","article_processing_charge":"No","publication":"Proceedings of the 41st International Conference on Machine Learning","researchdata_availability":"no","abstract":[{"text":"We introduce a new framework for studying meta-learning methods using PAC-Bayesian theory. Its main advantage over previous work is that it allows for more flexibility in how the transfer of knowledge between tasks is realized. For previous approaches, this could only happen indirectly, by means of learning prior distributions over models. In contrast, the new generalization bounds that we prove express the process of meta-learning much more directly as learning the learning algorithm that should be used for future tasks. The flexibility of our framework makes it suitable to analyze a wide range of meta-learning mechanisms and even design new mechanisms. Other than our theoretical contributions we also show empirically that our framework improves the prediction quality in practical meta-learning mechanisms.","lang":"eng"}],"das_tickbox":"0","supplementarymaterial":"no","intvolume":"       235","publication_identifier":{"eissn":["2640-3498"]},"date_updated":"2026-10-01T09:28:21Z","ddc":["000"],"date_published":"2024-09-01T00:00:00Z","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","title":"More flexible PAC-Bayesian meta-learning by learning learning algorithms","arxiv":1,"language":[{"iso":"eng"}],"_id":"18118","day":"01","status":"public","date_created":"2024-09-22T22:01:45Z","citation":{"ama":"Zakerinia H, Behjati A, Lampert C. More flexible PAC-Bayesian meta-learning by learning learning algorithms. In: <i>Proceedings of the 41st International Conference on Machine Learning</i>. Vol 235. ML Research Press; 2024:58122-58139.","short":"H. Zakerinia, A. Behjati, C. Lampert, in:, Proceedings of the 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 58122–58139.","apa":"Zakerinia, H., Behjati, A., &#38; Lampert, C. (2024). More flexible PAC-Bayesian meta-learning by learning learning algorithms. In <i>Proceedings of the 41st International Conference on Machine Learning</i> (Vol. 235, pp. 58122–58139). Vienna, Austria: ML Research Press.","mla":"Zakerinia, Hossein, et al. “More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms.” <i>Proceedings of the 41st International Conference on Machine Learning</i>, vol. 235, ML Research Press, 2024, pp. 58122–39.","chicago":"Zakerinia, Hossein, Amin Behjati, and Christoph Lampert. “More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms.” In <i>Proceedings of the 41st International Conference on Machine Learning</i>, 235:58122–39. ML Research Press, 2024.","ista":"Zakerinia H, Behjati A, Lampert C. 2024. More flexible PAC-Bayesian meta-learning by learning learning algorithms. Proceedings of the 41st International Conference on Machine Learning. ICML: International Conference on Machine Learning, PMLR, vol. 235, 58122–58139.","ieee":"H. Zakerinia, A. Behjati, and C. Lampert, “More flexible PAC-Bayesian meta-learning by learning learning algorithms,” in <i>Proceedings of the 41st International Conference on Machine Learning</i>, Vienna, Austria, 2024, vol. 235, pp. 58122–58139."},"year":"2024","department":[{"_id":"ChLa"}],"external_id":{"arxiv":["2402.04054"]},"month":"09","oa":1,"conference":{"location":"Vienna, Austria","end_date":"2024-07-27","name":"ICML: International Conference on Machine Learning","start_date":"2024-07-21"},"author":[{"last_name":"Zakerinia","id":"653bd8b6-f394-11eb-9cf6-c0bbf6cd78d4","first_name":"Hossein","orcid":"0009-0007-3977-6462","full_name":"Zakerinia, Hossein"},{"full_name":"Behjati, Amin","last_name":"Behjati","first_name":"Amin"},{"last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","first_name":"Christoph","orcid":"0000-0001-8622-7887","full_name":"Lampert, Christoph"}]},{"corr_author":"1","publication_status":"published","oa_version":"Preprint","page":"169-179","fulldoi":"https://doi.org/10.1109/IPDPS57955.2024.00023","type":"conference","publisher":"IEEE","main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2310.05293"}],"scopus_import":"1","researchdata_availability":"no","publication":"2024 IEEE International Parallel and Distributed Processing Symposium","abstract":[{"text":"Tree data structures, such as red-black trees, quad trees, treaps, or tries, are fundamental tools in computer science. A classical problem in concurrency is to obtain expressive, efficient, and scalable versions of practical tree data structures. We are interested in concurrent trees supporting range queries, i.e., queries that involve multiple consecutive data items. Existing implementations with this capability can list keys in a specific range, but do not support aggregate range queries: for instance, if we want to calculate the number of keys in a range, the only choice is to retrieve a whole list and return its size. This is suboptimal: in the sequential setting, one can augment a balanced search tree with counters and, consequently, perform these aggregate requests in logarithmic rather than linear time.In this paper, we propose a generic approach to implement a broad class of range queries on concurrent trees in a way that is wait-free, asymptotically efficient, and practically scalable. The key idea is a new mechanism for maintaining metadata concurrently at tree nodes, which can be seen as a wait-free variant of hand-over-hand locking (which we call hand-over-hand helping). We did a preliminary implementation of the wait-free binary search tree and preliminary experiments have indicated the soundness of our approach.","lang":"eng"}],"quality_controlled":"1","article_processing_charge":"No","doi":"10.1109/IPDPS57955.2024.00023","acknowledgement":"We thank Trevor Brown and Yuanhao Wei for the discussion and anonymous reviewers for helping us to improve the paper. Also, we thank JetBrains and Huawei for their support.","_id":"17332","language":[{"iso":"eng"}],"day":"08","isi":1,"title":"Wait-free trees with asymptotically-efficient range queries","arxiv":1,"user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","date_updated":"2026-10-01T09:30:18Z","date_published":"2024-07-08T00:00:00Z","das_tickbox":"0","publication_identifier":{"eissn":["1530-2075"],"isbn":["9798350337662"]},"supplementarymaterial":"no","oa":1,"conference":{"name":"IPDPS: International Parallel and Distributed Processing Symposium","end_date":"2024-05-31","location":"San Francisco, CA, United States","start_date":"2024-05-27"},"author":[{"full_name":"Kokorin, Ilya","last_name":"Kokorin","first_name":"Ilya"},{"first_name":"Victor","last_name":"Yudov","full_name":"Yudov, Victor"},{"full_name":"Aksenov, Vitaly","last_name":"Aksenov","first_name":"Vitaly"},{"full_name":"Alistarh, Dan-Adrian","orcid":"0000-0003-3650-940X","first_name":"Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","last_name":"Alistarh"}],"external_id":{"arxiv":["2310.05293"],"isi":["001270389600078"]},"month":"07","citation":{"ieee":"I. Kokorin, V. Yudov, V. Aksenov, and D.-A. Alistarh, “Wait-free trees with asymptotically-efficient range queries,” in <i>2024 IEEE International Parallel and Distributed Processing Symposium</i>, San Francisco, CA, United States, 2024, pp. 169–179.","ista":"Kokorin I, Yudov V, Aksenov V, Alistarh D-A. 2024. Wait-free trees with asymptotically-efficient range queries. 2024 IEEE International Parallel and Distributed Processing Symposium. IPDPS: International Parallel and Distributed Processing Symposium, 169–179.","chicago":"Kokorin, Ilya, Victor Yudov, Vitaly Aksenov, and Dan-Adrian Alistarh. “Wait-Free Trees with Asymptotically-Efficient Range Queries.” In <i>2024 IEEE International Parallel and Distributed Processing Symposium</i>, 169–79. IEEE, 2024. <a href=\"https://doi.org/10.1109/IPDPS57955.2024.00023\">https://doi.org/10.1109/IPDPS57955.2024.00023</a>.","apa":"Kokorin, I., Yudov, V., Aksenov, V., &#38; Alistarh, D.-A. (2024). Wait-free trees with asymptotically-efficient range queries. In <i>2024 IEEE International Parallel and Distributed Processing Symposium</i> (pp. 169–179). San Francisco, CA, United States: IEEE. <a href=\"https://doi.org/10.1109/IPDPS57955.2024.00023\">https://doi.org/10.1109/IPDPS57955.2024.00023</a>","short":"I. Kokorin, V. Yudov, V. Aksenov, D.-A. Alistarh, in:, 2024 IEEE International Parallel and Distributed Processing Symposium, IEEE, 2024, pp. 169–179.","ama":"Kokorin I, Yudov V, Aksenov V, Alistarh D-A. Wait-free trees with asymptotically-efficient range queries. In: <i>2024 IEEE International Parallel and Distributed Processing Symposium</i>. IEEE; 2024:169-179. doi:<a href=\"https://doi.org/10.1109/IPDPS57955.2024.00023\">10.1109/IPDPS57955.2024.00023</a>","mla":"Kokorin, Ilya, et al. “Wait-Free Trees with Asymptotically-Efficient Range Queries.” <i>2024 IEEE International Parallel and Distributed Processing Symposium</i>, IEEE, 2024, pp. 169–79, doi:<a href=\"https://doi.org/10.1109/IPDPS57955.2024.00023\">10.1109/IPDPS57955.2024.00023</a>."},"date_created":"2024-07-28T22:01:11Z","year":"2024","department":[{"_id":"DaAl"}],"status":"public"},{"title":"How to prune your language model: Recovering accuracy on the \"Sparsity May Cry\" benchmark","arxiv":1,"language":[{"iso":"eng"}],"_id":"15011","day":"08","das_tickbox":"0","publication_identifier":{"eissn":["2640-3498"]},"intvolume":"       234","supplementarymaterial":"no","date_updated":"2026-10-01T09:31:02Z","date_published":"2024-01-08T00:00:00Z","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","external_id":{"arxiv":["2312.13547"]},"month":"01","oa":1,"author":[{"full_name":"Kurtic, Eldar","id":"47beb3a5-07b5-11eb-9b87-b108ec578218","last_name":"Kurtic","first_name":"Eldar"},{"last_name":"Hoefler","first_name":"Torsten","full_name":"Hoefler, Torsten"},{"full_name":"Alistarh, Dan-Adrian","orcid":"0000-0003-3650-940X","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","last_name":"Alistarh","first_name":"Dan-Adrian"}],"conference":{"location":"Hongkong, China","end_date":"2024-01-06","name":"CPAL: Conference on Parsimony and Learning","start_date":"2024-01-03"},"status":"public","year":"2024","date_created":"2024-02-18T23:01:03Z","citation":{"chicago":"Kurtic, Eldar, Torsten Hoefler, and Dan-Adrian Alistarh. “How to Prune Your Language Model: Recovering Accuracy on the ‘Sparsity May Cry’ Benchmark.” In <i>Proceedings of Machine Learning Research</i>, 234:542–53. ML Research Press, 2024.","ista":"Kurtic E, Hoefler T, Alistarh D-A. 2024. How to prune your language model: Recovering accuracy on the ‘Sparsity May Cry’ benchmark. Proceedings of Machine Learning Research. CPAL: Conference on Parsimony and Learning, PMLR, vol. 234, 542–553.","ieee":"E. Kurtic, T. Hoefler, and D.-A. Alistarh, “How to prune your language model: Recovering accuracy on the ‘Sparsity May Cry’ benchmark,” in <i>Proceedings of Machine Learning Research</i>, Hongkong, China, 2024, vol. 234, pp. 542–553.","ama":"Kurtic E, Hoefler T, Alistarh D-A. How to prune your language model: Recovering accuracy on the “Sparsity May Cry” benchmark. In: <i>Proceedings of Machine Learning Research</i>. Vol 234. ML Research Press; 2024:542-553.","short":"E. Kurtic, T. Hoefler, D.-A. Alistarh, in:, Proceedings of Machine Learning Research, ML Research Press, 2024, pp. 542–553.","apa":"Kurtic, E., Hoefler, T., &#38; Alistarh, D.-A. (2024). How to prune your language model: Recovering accuracy on the “Sparsity May Cry” benchmark. In <i>Proceedings of Machine Learning Research</i> (Vol. 234, pp. 542–553). Hongkong, China: ML Research Press.","mla":"Kurtic, Eldar, et al. “How to Prune Your Language Model: Recovering Accuracy on the ‘Sparsity May Cry’ Benchmark.” <i>Proceedings of Machine Learning Research</i>, vol. 234, ML Research Press, 2024, pp. 542–53."},"department":[{"_id":"DaAl"}],"alternative_title":["PMLR"],"volume":234,"page":"542-553","corr_author":"1","oa_version":"Preprint","publication_status":"published","publisher":"ML Research Press","scopus_import":"1","main_file_link":[{"open_access":"1","url":"https://proceedings.mlr.press/v234/kurtic24a"}],"type":"conference","quality_controlled":"1","article_processing_charge":"No","publication":"Proceedings of Machine Learning Research","researchdata_availability":"no","abstract":[{"text":"Pruning large language models (LLMs) from the BERT family has emerged as a standard compression benchmark, and several pruning methods have been proposed for this task. The recent “Sparsity May Cry” (SMC) benchmark put into question the validity of all existing methods, exhibiting a more complex setup where many known pruning methods appear to fail. We revisit the question of accurate BERT-pruning during fine-tuning on downstream datasets, and propose a set of general guidelines for successful pruning, even on the challenging SMC benchmark. First, we perform a cost-vs-benefits analysis of pruning model components, such as the embeddings and the classification head; second, we provide a simple-yet-general way of scaling training, sparsification and learning rate schedules relative to the desired target sparsity; finally, we investigate the importance of proper parametrization for Knowledge Distillation in the context of LLMs. Our simple insights lead to state-of-the-art results, both on classic BERT-pruning benchmarks, as well as on the SMC benchmark, showing that even classic gradual magnitude pruning (GMP) can yield competitive results, with the right approach.","lang":"eng"}]},{"title":"Federated SGD with local asynchrony","language":[{"iso":"eng"}],"_id":"18070","day":"26","isi":1,"das_tickbox":"0","supplementarymaterial":"no","publication_identifier":{"eissn":["2575-8411"],"issn":["1063-6927"],"isbn":["9798350386059"]},"user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","date_updated":"2026-10-01T09:32:24Z","date_published":"2024-07-26T00:00:00Z","external_id":{"isi":["001304430200075"]},"month":"07","conference":{"start_date":"2024-07-23","name":"ICDCS: International Conference on Distributed Computing Systems","end_date":"2024-07-26","location":"Jersey City, NJ, United States"},"author":[{"orcid":"0000-0002-2742-4028","full_name":"Chatterjee, Bapi","first_name":"Bapi","id":"3C41A08A-F248-11E8-B48F-1D18A9856A87","last_name":"Chatterjee"},{"last_name":"Kungurtsev","first_name":"Vyacheslav","full_name":"Kungurtsev, Vyacheslav"},{"id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","last_name":"Alistarh","first_name":"Dan-Adrian","full_name":"Alistarh, Dan-Adrian","orcid":"0000-0003-3650-940X"}],"status":"public","citation":{"mla":"Chatterjee, Bapi, et al. “Federated SGD with Local Asynchrony.” <i>Proceedings of the 44th International Conference on Distributed Computing Systems</i>, IEEE, 2024, pp. 857–68, doi:<a href=\"https://doi.org/10.1109/ICDCS60910.2024.00084\">10.1109/ICDCS60910.2024.00084</a>.","apa":"Chatterjee, B., Kungurtsev, V., &#38; Alistarh, D.-A. (2024). Federated SGD with local asynchrony. In <i>Proceedings of the 44th International Conference on Distributed Computing Systems</i> (pp. 857–868). Jersey City, NJ, United States: IEEE. <a href=\"https://doi.org/10.1109/ICDCS60910.2024.00084\">https://doi.org/10.1109/ICDCS60910.2024.00084</a>","short":"B. Chatterjee, V. Kungurtsev, D.-A. Alistarh, in:, Proceedings of the 44th International Conference on Distributed Computing Systems, IEEE, 2024, pp. 857–868.","ama":"Chatterjee B, Kungurtsev V, Alistarh D-A. Federated SGD with local asynchrony. In: <i>Proceedings of the 44th International Conference on Distributed Computing Systems</i>. IEEE; 2024:857-868. doi:<a href=\"https://doi.org/10.1109/ICDCS60910.2024.00084\">10.1109/ICDCS60910.2024.00084</a>","ieee":"B. Chatterjee, V. Kungurtsev, and D.-A. Alistarh, “Federated SGD with local asynchrony,” in <i>Proceedings of the 44th International Conference on Distributed Computing Systems</i>, Jersey City, NJ, United States, 2024, pp. 857–868.","chicago":"Chatterjee, Bapi, Vyacheslav Kungurtsev, and Dan-Adrian Alistarh. “Federated SGD with Local Asynchrony.” In <i>Proceedings of the 44th International Conference on Distributed Computing Systems</i>, 857–68. IEEE, 2024. <a href=\"https://doi.org/10.1109/ICDCS60910.2024.00084\">https://doi.org/10.1109/ICDCS60910.2024.00084</a>.","ista":"Chatterjee B, Kungurtsev V, Alistarh D-A. 2024. Federated SGD with local asynchrony. Proceedings of the 44th International Conference on Distributed Computing Systems. ICDCS: International Conference on Distributed Computing Systems, 857–868."},"date_created":"2024-09-15T22:01:41Z","year":"2024","department":[{"_id":"DaAl"}],"page":"857-868","corr_author":"1","publication_status":"published","oa_version":"None","publisher":"IEEE","scopus_import":"1","fulldoi":"https://doi.org/10.1109/ICDCS60910.2024.00084","type":"conference","quality_controlled":"1","article_processing_charge":"No","publication":"Proceedings of the 44th International Conference on Distributed Computing Systems","researchdata_availability":"yes","abstract":[{"lang":"eng","text":"Parallel SGD in a shared-memory setting is oft-represented by the popular Hogwild! algorithm, in which lock-free updates are asynchronously performed by multiple computing processes. Unfortunately, scaling Hogwild! to distributed workers is largely unexplored. Specifically, it is unknown if any adaptation of Hogwild! to the popular decentralized multi-GPU setting offers any competitive speedup, either empirically or theoretically. In this work, we investigate the potential of decentralizing Hogwild! by incorporating simultaneously (a) asynchronous local gradient updates on the shared memory of GPUs, and (b) non-blocking asynchronous decentralized federated averaging. A naive direct implementation shows degradation in performance, arising from scheduling overheads and concurrent write conflicts on GPUs. To mitigate these drawbacks, we investigate and propose a new method, based on careful block selection rules, which update only portions of the parameter vectors. Our experiments show that the resulting decentralized training method exhibits improved throughput and competitive accuracy for standard image classification benchmarks on the CIFAR-10, CIFAR-100, and Imagenet datasets. On the theoretical side, we prove that our method guarantees sublinear ergodic convergence rates for non-convex objectives."}],"doi":"10.1109/ICDCS60910.2024.00084"},{"status":"public","department":[{"_id":"DaAl"},{"_id":"KrCh"}],"citation":{"mla":"Alistarh, Dan-Adrian, et al. “Game Dynamics and Equilibrium Computation in the Population Protocol Model.” <i>Proceedings of the 43rd Annual ACM Symposium on Principles of Distributed Computing</i>, Association for Computing Machinery, 2024, pp. 40–49, doi:<a href=\"https://doi.org/10.1145/3662158.3662768\">10.1145/3662158.3662768</a>.","short":"D.-A. Alistarh, K. Chatterjee, M. Karrabi, J.M. Lazarsfeld, in:, Proceedings of the 43rd Annual ACM Symposium on Principles of Distributed Computing, Association for Computing Machinery, 2024, pp. 40–49.","apa":"Alistarh, D.-A., Chatterjee, K., Karrabi, M., &#38; Lazarsfeld, J. M. (2024). Game dynamics and equilibrium computation in the population protocol model. In <i>Proceedings of the 43rd Annual ACM Symposium on Principles of Distributed Computing</i> (pp. 40–49). Nantes, France: Association for Computing Machinery. <a href=\"https://doi.org/10.1145/3662158.3662768\">https://doi.org/10.1145/3662158.3662768</a>","ama":"Alistarh D-A, Chatterjee K, Karrabi M, Lazarsfeld JM. Game dynamics and equilibrium computation in the population protocol model. In: <i>Proceedings of the 43rd Annual ACM Symposium on Principles of Distributed Computing</i>. Association for Computing Machinery; 2024:40-49. doi:<a href=\"https://doi.org/10.1145/3662158.3662768\">10.1145/3662158.3662768</a>","ieee":"D.-A. Alistarh, K. Chatterjee, M. Karrabi, and J. M. Lazarsfeld, “Game dynamics and equilibrium computation in the population protocol model,” in <i>Proceedings of the 43rd Annual ACM Symposium on Principles of Distributed Computing</i>, Nantes, France, 2024, pp. 40–49.","ista":"Alistarh D-A, Chatterjee K, Karrabi M, Lazarsfeld JM. 2024. Game dynamics and equilibrium computation in the population protocol model. Proceedings of the 43rd Annual ACM Symposium on Principles of Distributed Computing. PODC: Symposium on Principles of Distributed Computing, 40–49.","chicago":"Alistarh, Dan-Adrian, Krishnendu Chatterjee, Mehrdad Karrabi, and John M Lazarsfeld. “Game Dynamics and Equilibrium Computation in the Population Protocol Model.” In <i>Proceedings of the 43rd Annual ACM Symposium on Principles of Distributed Computing</i>, 40–49. Association for Computing Machinery, 2024. <a href=\"https://doi.org/10.1145/3662158.3662768\">https://doi.org/10.1145/3662158.3662768</a>."},"date_created":"2024-07-28T22:01:10Z","year":"2024","month":"06","conference":{"end_date":"2024-06-21","name":"PODC: Symposium on Principles of Distributed Computing","location":"Nantes, France","start_date":"2024-06-17"},"author":[{"full_name":"Alistarh, Dan-Adrian","orcid":"0000-0003-3650-940X","first_name":"Dan-Adrian","last_name":"Alistarh","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87"},{"full_name":"Chatterjee, Krishnendu","orcid":"0000-0002-4561-241X","first_name":"Krishnendu","id":"2E5DCA20-F248-11E8-B48F-1D18A9856A87","last_name":"Chatterjee"},{"orcid":"0009-0007-5253-9170","full_name":"Karrabi, Mehrdad","id":"67638922-f394-11eb-9cf6-f20423e08757","last_name":"Karrabi","first_name":"Mehrdad"},{"full_name":"Lazarsfeld, John M","id":"17ce3656-183e-11ef-84c3-8932383e1b23","last_name":"Lazarsfeld","first_name":"John M"}],"oa":1,"has_accepted_license":"1","file_date_updated":"2024-07-29T07:37:31Z","publication_identifier":{"isbn":["9798400706684"]},"supplementarymaterial":"no","das_tickbox":"0","date_published":"2024-06-17T00:00:00Z","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","ddc":["000"],"date_updated":"2026-10-01T09:34:57Z","title":"Game dynamics and equilibrium computation in the population protocol model","day":"17","language":[{"iso":"eng"}],"_id":"17329","file":[{"relation":"main_file","success":1,"file_id":"17335","file_name":"2024_ACMPODC_Alistarh.pdf","creator":"dernst","checksum":"65a40437f83373fa79dd999d5287509e","file_size":750908,"access_level":"open_access","content_type":"application/pdf","date_updated":"2024-07-29T07:37:31Z","date_created":"2024-07-29T07:37:31Z"}],"acknowledgement":"This work was supported in part by the ERC-2020-CoG 863818 (FoRM-SMArt) grant. We thank James Aspnes and Thomas Sauerwald for several helpful discussions on Ehrenfest random walks.","doi":"10.1145/3662158.3662768","article_processing_charge":"Yes (via OA deal)","quality_controlled":"1","abstract":[{"text":"We initiate the study of game dynamics in the population protocol model: n agents each maintain a current local strategy and interact in pairs uniformly at random. Upon each interaction, the agents play a two-person game and receive a payoff from an underlying utility function, and they can subsequently update their strategies according to a fixed local algorithm. In this setting, we ask how the distribution over agent strategies evolves over a sequence of interactions, and we introduce a new distributional equilibrium concept to quantify the quality of such distributions. As an initial example, we study a class of repeated prisoner's dilemma games, and we consider a family of simple local update algorithms that yield non-trivial dynamics over the distribution of agent strategies. We show that these dynamics are related to a new class of high-dimensional Ehrenfest random walks, and we derive exact characterizations of their stationary distributions, bounds on their mixing times, and prove their convergence to approximate distributional equilibria. Our results highlight trade-offs between the local state space of each agent, and the convergence rate and approximation factor of the underlying dynamics. Our approach opens the door towards the further characterization of equilibrium computation for other classes of games and dynamics in the population setting.","lang":"eng"}],"project":[{"name":"Formal Methods for Stochastic Models: Algorithms and Applications","grant_number":"863818","_id":"0599E47C-7A3F-11EA-A408-12923DDC885E","call_identifier":"H2020"}],"researchdata_availability":"no","publication":"Proceedings of the 43rd Annual ACM Symposium on Principles of Distributed Computing","scopus_import":"1","tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","image":"/images/cc_by.png","short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"publisher":"Association for Computing Machinery","fulldoi":"https://doi.org/10.1145/3662158.3662768","ec_funded":1,"type":"conference","page":"40-49","publication_status":"published","oa_version":"Published Version","corr_author":"1"},{"volume":235,"alternative_title":["PMLR"],"page":"45955-45987","acknowledged_ssus":[{"_id":"ScienComp"}],"corr_author":"1","oa_version":"Preprint","publication_status":"published","publisher":"ML Research Press","scopus_import":"1","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2310.04519","open_access":"1"}],"type":"conference","quality_controlled":"1","article_processing_charge":"No","publication":"Proceedings of the 41st International Conference on Machine Learning","project":[{"_id":"9B9290DE-BA93-11EA-9121-9846C619BF3A","name":"Vienna Graduate School on Computational Optimization","grant_number":"W1260-N35"}],"researchdata_availability":"yes","abstract":[{"text":"It is known that sparsity can improve interpretability for deep neural networks. However, existing methods in the area either require networks that are pre-trained with sparsity constraints, or impose sparsity after the fact, altering the network’s general behavior. In this paper, we demonstrate, for the first time, that sparsity can instead be incorporated into the interpretation process itself, as a sample-specific preprocessing step. Unlike previous work, this approach, which we call SPADE, does not place constraints on the trained model and does not affect its behavior during inference on the sample. Given a trained model and a target sample, SPADE uses sample-targeted pruning to provide a \"trace\" of the network’s execution on the sample, reducing the network to the most important connections prior to computing an interpretation. We demonstrate that preprocessing with SPADE significantly increases the accuracy of image saliency maps across several interpretability methods. Additionally, SPADE improves the usefulness of neuron visualizations, aiding humans in reasoning about network behavior. Our code is available at https://github.com/IST-DASLab/SPADE.","lang":"eng"}],"related_material":{"record":[{"id":"21854","status":"public","relation":"dissertation_contains"}],"link":[{"relation":"software","url":"https://github.com/IST-DASLab/SPADE"}]},"acknowledgement":"The authors would like to thank Stephen Casper and Tony Wang for their feedback on this work, and Eldar Kurtic for his advice on aspects of the project. This research was supported by the Scientific Service Units (SSU) of IST Austria through resources provided by Scientific Computing (SciComp). EI was supported in part by the FWF DK VGSCO, grant agreement number W1260-N35.","title":"SPADE: Sparsity-guided debugging for deep neural networks","arxiv":1,"language":[{"iso":"eng"}],"_id":"18121","day":"01","das_tickbox":"0","publication_identifier":{"eissn":["2640-3498"]},"intvolume":"       235","supplementarymaterial":"no","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","date_published":"2024-09-01T00:00:00Z","date_updated":"2026-10-01T09:32:47Z","external_id":{"arxiv":["2310.04519"]},"month":"09","oa":1,"author":[{"last_name":"Moakhar","first_name":"Arshia Soltani","full_name":"Moakhar, Arshia Soltani"},{"orcid":"0000-0002-7778-3221","full_name":"Iofinova, Eugenia B","last_name":"Iofinova","id":"f9a17499-f6e0-11ea-865d-fdf9a3f77117","first_name":"Eugenia B"},{"first_name":"Elias","id":"09a8f98d-ec99-11ea-ae11-c063a7b7fe5f","last_name":"Frantar","full_name":"Frantar, Elias"},{"first_name":"Dan-Adrian","last_name":"Alistarh","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","full_name":"Alistarh, Dan-Adrian","orcid":"0000-0003-3650-940X"}],"conference":{"start_date":"2024-07-21","location":"Vienna, Austria","name":"ICML: International Conference on Machine Learning","end_date":"2024-07-27"},"status":"public","year":"2024","citation":{"chicago":"Moakhar, Arshia Soltani, Eugenia B Iofinova, Elias Frantar, and Dan-Adrian Alistarh. “SPADE: Sparsity-Guided Debugging for Deep Neural Networks.” In <i>Proceedings of the 41st International Conference on Machine Learning</i>, 235:45955–87. ML Research Press, 2024.","ista":"Moakhar AS, Iofinova EB, Frantar E, Alistarh D-A. 2024. SPADE: Sparsity-guided debugging for deep neural networks. Proceedings of the 41st International Conference on Machine Learning. ICML: International Conference on Machine Learning, PMLR, vol. 235, 45955–45987.","ieee":"A. S. Moakhar, E. B. Iofinova, E. Frantar, and D.-A. Alistarh, “SPADE: Sparsity-guided debugging for deep neural networks,” in <i>Proceedings of the 41st International Conference on Machine Learning</i>, Vienna, Austria, 2024, vol. 235, pp. 45955–45987.","mla":"Moakhar, Arshia Soltani, et al. “SPADE: Sparsity-Guided Debugging for Deep Neural Networks.” <i>Proceedings of the 41st International Conference on Machine Learning</i>, vol. 235, ML Research Press, 2024, pp. 45955–87.","ama":"Moakhar AS, Iofinova EB, Frantar E, Alistarh D-A. SPADE: Sparsity-guided debugging for deep neural networks. In: <i>Proceedings of the 41st International Conference on Machine Learning</i>. Vol 235. ML Research Press; 2024:45955-45987.","apa":"Moakhar, A. S., Iofinova, E. B., Frantar, E., &#38; Alistarh, D.-A. (2024). SPADE: Sparsity-guided debugging for deep neural networks. In <i>Proceedings of the 41st International Conference on Machine Learning</i> (Vol. 235, pp. 45955–45987). Vienna, Austria: ML Research Press.","short":"A.S. Moakhar, E.B. Iofinova, E. Frantar, D.-A. Alistarh, in:, Proceedings of the 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 45955–45987."},"date_created":"2024-09-22T22:01:46Z","department":[{"_id":"DaAl"}]},{"oa":1,"conference":{"start_date":"2024-05-02","location":"Valencia, Spain","end_date":"2024-05-04","name":"AISTATS: Conference on Artificial Intelligence and Statistics"},"author":[{"first_name":"Rustem","last_name":"Islamov","full_name":"Islamov, Rustem"},{"first_name":"Mher","last_name":"Safaryan","id":"dd546b39-0804-11ed-9c55-ef075c39778d","full_name":"Safaryan, Mher"},{"orcid":"0000-0003-3650-940X","full_name":"Alistarh, Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","last_name":"Alistarh","first_name":"Dan-Adrian"}],"external_id":{"arxiv":["2310.20452"]},"month":"05","date_created":"2025-01-30T08:15:49Z","citation":{"ieee":"R. Islamov, M. Safaryan, and D.-A. Alistarh, “AsGrad: A sharp unified analysis of asynchronous-SGD algorithms,” in <i>Proceedings of The 27th International Conference on Artificial Intelligence and Statistics</i>, Valencia, Spain, 2024, vol. 238, pp. 649–657.","ista":"Islamov R, Safaryan M, Alistarh D-A. 2024. AsGrad: A sharp unified analysis of asynchronous-SGD algorithms. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics. AISTATS: Conference on Artificial Intelligence and Statistics, PMLR, vol. 238, 649–657.","chicago":"Islamov, Rustem, Mher Safaryan, and Dan-Adrian Alistarh. “AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms.” In <i>Proceedings of The 27th International Conference on Artificial Intelligence and Statistics</i>, 238:649–57. ML Research Press, 2024.","short":"R. Islamov, M. Safaryan, D.-A. Alistarh, in:, Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, ML Research Press, 2024, pp. 649–657.","apa":"Islamov, R., Safaryan, M., &#38; Alistarh, D.-A. (2024). AsGrad: A sharp unified analysis of asynchronous-SGD algorithms. In <i>Proceedings of The 27th International Conference on Artificial Intelligence and Statistics</i> (Vol. 238, pp. 649–657). Valencia, Spain: ML Research Press.","ama":"Islamov R, Safaryan M, Alistarh D-A. AsGrad: A sharp unified analysis of asynchronous-SGD algorithms. In: <i>Proceedings of The 27th International Conference on Artificial Intelligence and Statistics</i>. Vol 238. ML Research Press; 2024:649-657.","mla":"Islamov, Rustem, et al. “AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms.” <i>Proceedings of The 27th International Conference on Artificial Intelligence and Statistics</i>, vol. 238, ML Research Press, 2024, pp. 649–57."},"year":"2024","OA_type":"green","department":[{"_id":"DaAl"}],"status":"public","language":[{"iso":"eng"}],"_id":"18976","day":"15","title":"AsGrad: A sharp unified analysis of asynchronous-SGD algorithms","arxiv":1,"user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","date_published":"2024-05-15T00:00:00Z","date_updated":"2026-10-01T09:33:24Z","OA_place":"repository","das_tickbox":"0","supplementarymaterial":"no","publication_identifier":{"eissn":["2640-3498"]},"intvolume":"       238","researchdata_availability":"no","project":[{"grant_number":"101034413","name":"IST-BRIDGE: International postdoctoral program","_id":"fc2ed2f7-9c52-11eb-aca3-c01059dda49c","call_identifier":"H2020"}],"publication":"Proceedings of The 27th International Conference on Artificial Intelligence and Statistics","abstract":[{"lang":"eng","text":"We analyze asynchronous-type algorithms for distributed SGD in the heterogeneous setting, where each worker has its own computation and communication speeds, as well as data distribution. In these algorithms, workers compute possibly stale and stochastic gradients associated with their local data at some iteration back in history and then return those gradients to the server without synchronizing with other workers. We present a unified convergence theory for non-convex smooth functions in the heterogeneous regime. The proposed analysis provides convergence for pure asynchronous SGD and its various modifications. Moreover, our theory explains what affects the convergence rate and what can be done to improve the performance of asynchronous algorithms. In particular, we introduce a novel asynchronous method based on worker shuffling. As a by-product of our analysis, we also demonstrate convergence guarantees for gradient-type algorithms such as SGD with random reshuffling and shuffle-once mini-batch SGD. The derived rates match the best-known results for those algorithms, highlighting the tightness of our approach. Finally, our numerical evaluations support theoretical findings and show the good practical performance of our method."}],"quality_controlled":"1","article_processing_charge":"No","acknowledgement":"The authors thank all anonymous reviewers for their valuable comments and suggestions on how to improve the manuscript. This work was done when Rustem Islamov was a Master’s student at Institut Polytechnique de Paris (IP Paris) and an intern at Institute of Science and Technology Austria (ISTA). The research of Rustem Islamov was supported by ISTA internship\r\nprogram. Mher Safaryan has received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Skłodowska-Curie grant agreement No 101034413.","corr_author":"1","publication_status":"published","oa_version":"Preprint","page":"649-657","volume":238,"alternative_title":["PMLR"],"ec_funded":1,"type":"conference","publisher":"ML Research Press","scopus_import":"1","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2310.20452","open_access":"1"}]},{"year":"2024","date_created":"2024-09-22T22:01:43Z","citation":{"short":"V. Egiazarian, A. Panferov, D. Kuznedelev, E. Frantar, A. Babenko, D.-A. Alistarh, in:, Proceedings of the 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 12284–12303.","apa":"Egiazarian, V., Panferov, A., Kuznedelev, D., Frantar, E., Babenko, A., &#38; Alistarh, D.-A. (2024). Extreme compression of large language models via additive quantization. In <i>Proceedings of the 41st International Conference on Machine Learning</i> (Vol. 235, pp. 12284–12303). Vienna, Austria: ML Research Press.","ama":"Egiazarian V, Panferov A, Kuznedelev D, Frantar E, Babenko A, Alistarh D-A. Extreme compression of large language models via additive quantization. In: <i>Proceedings of the 41st International Conference on Machine Learning</i>. Vol 235. ML Research Press; 2024:12284-12303.","mla":"Egiazarian, Vage, et al. “Extreme Compression of Large Language Models via Additive Quantization.” <i>Proceedings of the 41st International Conference on Machine Learning</i>, vol. 235, ML Research Press, 2024, pp. 12284–303.","ieee":"V. Egiazarian, A. Panferov, D. Kuznedelev, E. Frantar, A. Babenko, and D.-A. Alistarh, “Extreme compression of large language models via additive quantization,” in <i>Proceedings of the 41st International Conference on Machine Learning</i>, Vienna, Austria, 2024, vol. 235, pp. 12284–12303.","chicago":"Egiazarian, Vage, Andrei Panferov, Denis Kuznedelev, Elias Frantar, Artem Babenko, and Dan-Adrian Alistarh. “Extreme Compression of Large Language Models via Additive Quantization.” In <i>Proceedings of the 41st International Conference on Machine Learning</i>, 235:12284–303. ML Research Press, 2024.","ista":"Egiazarian V, Panferov A, Kuznedelev D, Frantar E, Babenko A, Alistarh D-A. 2024. Extreme compression of large language models via additive quantization. Proceedings of the 41st International Conference on Machine Learning. ICML: International Conference on Machine Learning, PMLR, vol. 235, 12284–12303."},"department":[{"_id":"DaAl"},{"_id":"GradSch"}],"status":"public","oa":1,"author":[{"last_name":"Egiazarian","first_name":"Vage","full_name":"Egiazarian, Vage"},{"id":"2c18daae-4dbe-11ef-8491-98ce2d960f09","last_name":"Panferov","first_name":"Andrei","full_name":"Panferov, Andrei"},{"full_name":"Kuznedelev, Denis","first_name":"Denis","last_name":"Kuznedelev"},{"full_name":"Frantar, Elias","first_name":"Elias","last_name":"Frantar","id":"09a8f98d-ec99-11ea-ae11-c063a7b7fe5f"},{"full_name":"Babenko, Artem","first_name":"Artem","last_name":"Babenko"},{"orcid":"0000-0003-3650-940X","full_name":"Alistarh, Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","last_name":"Alistarh","first_name":"Dan-Adrian"}],"conference":{"start_date":"2024-07-21","end_date":"2024-07-27","name":"ICML: International Conference on Machine Learning","location":"Vienna, Austria"},"external_id":{"arxiv":["2401.06118"]},"month":"09","date_published":"2024-09-01T00:00:00Z","date_updated":"2026-10-01T09:34:19Z","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","das_tickbox":"0","intvolume":"       235","supplementarymaterial":"no","publication_identifier":{"eissn":["2640-3498"]},"language":[{"iso":"eng"}],"_id":"18113","day":"01","title":"Extreme compression of large language models via additive quantization","arxiv":1,"acknowledgement":"Authors would like to thank Ruslan Svirschevski for his help in solving technical issues with AQLM and baselines. We also thank Tim Dettmers for helpful discussions on the structure of weights in modern LLMs and size-accuracy trade-offs. The authors would also like to thank Daniil Pavlov for his assistance with CPU benchmarking. Finally, authors would like to thank the communities of ML enthusiasts known as LocalLLaMA5 and Petals community on discord6\r\nfor the crowd wisdom about running LLMs on consumer devices. Egiazarian Vage and Denis Kuznedelev and Andrei Panferov were supported by the grant for research centers in the field of AI provided by the Analytical Center for the Government of the Russian Federation (ACRF) in\r\naccordance with the agreement on the provision of subsidies (identifier of the agreement 000000D730321P5Q0002) and the agreement with HSE University No. 70-2021-00139.","researchdata_availability":"no","publication":"Proceedings of the 41st International Conference on Machine Learning","abstract":[{"text":"The emergence of accurate open large language models (LLMs) has led to a race towards performant quantization techniques which can enable their execution on end-user devices. In this paper, we revisit the problem of “extreme” LLM compression—defined as targeting extremely low bit counts, such as 2 to 3 bits per parameter—from the point of view of classic methods in Multi-Codebook Quantization (MCQ). Our algorithm, called AQLM, generalizes the classic Additive Quantization (AQ) approach for information retrieval to advance the state-of-the-art in LLM compression, via two innovations: 1) learned additive quantization of weight matrices in input-adaptive fashion, and 2) joint optimization of codebook parameters across each transformer blocks. Broadly, AQLM is the first scheme that is Pareto optimal in terms of accuracy-vs-model-size when compressing to less than 3 bits per parameter, and significantly improves upon all known schemes in the extreme compression (2bit) regime. In addition, AQLM is practical: we provide fast GPU and CPU implementations of AQLM for token generation, which enable us to match or outperform optimized FP16 implementations for speed, while executing in a much smaller memory footprint.","lang":"eng"}],"quality_controlled":"1","article_processing_charge":"No","type":"conference","publisher":"ML Research Press","scopus_import":"1","main_file_link":[{"open_access":"1","url":" https://doi.org/10.48550/arXiv.2401.06118"}],"corr_author":"1","oa_version":"Preprint","publication_status":"published","alternative_title":["PMLR"],"volume":235,"page":"12284-12303"},{"main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2306.06098"}],"scopus_import":"1","publisher":"ML Research Press","type":"conference","acknowledged_ssus":[{"_id":"CampIT"}],"volume":235,"alternative_title":["PMLR"],"page":"35910-35933","oa_version":"Preprint","publication_status":"published","corr_author":"1","acknowledgement":"The authors thank Adrian Vladu, Razvan Pascanu, Alexandra Peste, Mher Safaryan for their valuable feedback, the IT department from Institute of Science and Technology Austria for the hardware support and Weights and Biases for the infrastructure to track all our experiments.","article_processing_charge":"No","quality_controlled":"1","abstract":[{"lang":"eng","text":"Leveraging second-order information about the loss at the scale of deep networks is one of the main lines of approach for improving the performance of current optimizers for deep learning. Yet, existing approaches for accurate full-matrix preconditioning, such as Full-Matrix Adagrad (GGT) or Matrix-Free Approximate Curvature (M-FAC) suffer from massive storage costs when applied even to small-scale models, as they must store a sliding window of gradients, whose memory requirements are multiplicative in the model dimension. In this paper, we address this issue via a novel and efficient error-feedback technique that can be applied to compress preconditioners by up to two orders of magnitude in practice, without loss of convergence. Specifically, our approach compresses the gradient information via sparsification or low-rank compression before it is fed into the preconditioner, feeding the compression error back into future iterations. Extensive experiments on deep neural networks show that this approach can compress full-matrix preconditioners to up to 99% sparsity without accuracy loss, effectively removing the memory overhead of fullmatrix preconditioners such as GGT and M-FAC."}],"researchdata_availability":"yes","publication":"41st International Conference on Machine Learning","supplementarymaterial":"no","publication_identifier":{"eissn":["2640-3498"]},"intvolume":"       235","OA_place":"repository","das_tickbox":"0","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","date_published":"2024-07-30T00:00:00Z","date_updated":"2026-10-01T09:33:07Z","arxiv":1,"title":"Error feedback can accurately compress preconditioners","day":"30","language":[{"iso":"eng"}],"_id":"18975","status":"public","department":[{"_id":"DaAl"}],"OA_type":"green","year":"2024","citation":{"ieee":"I.-V. Modoranu, A. Kalinov, E. Kurtic, E. Frantar, and D.-A. Alistarh, “Error feedback can accurately compress preconditioners,” in <i>41st International Conference on Machine Learning</i>, Vienna, Austria, 2024, vol. 235, pp. 35910–35933.","ista":"Modoranu I-V, Kalinov A, Kurtic E, Frantar E, Alistarh D-A. 2024. Error feedback can accurately compress preconditioners. 41st International Conference on Machine Learning. ICML: International Conference on Machine Learning, PMLR, vol. 235, 35910–35933.","chicago":"Modoranu, Ionut-Vlad, Aleksei Kalinov, Eldar Kurtic, Elias Frantar, and Dan-Adrian Alistarh. “Error Feedback Can Accurately Compress Preconditioners.” In <i>41st International Conference on Machine Learning</i>, 235:35910–33. ML Research Press, 2024.","short":"I.-V. Modoranu, A. Kalinov, E. Kurtic, E. Frantar, D.-A. Alistarh, in:, 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 35910–35933.","apa":"Modoranu, I.-V., Kalinov, A., Kurtic, E., Frantar, E., &#38; Alistarh, D.-A. (2024). Error feedback can accurately compress preconditioners. In <i>41st International Conference on Machine Learning</i> (Vol. 235, pp. 35910–35933). Vienna, Austria: ML Research Press.","ama":"Modoranu I-V, Kalinov A, Kurtic E, Frantar E, Alistarh D-A. Error feedback can accurately compress preconditioners. In: <i>41st International Conference on Machine Learning</i>. Vol 235. ML Research Press; 2024:35910-35933.","mla":"Modoranu, Ionut-Vlad, et al. “Error Feedback Can Accurately Compress Preconditioners.” <i>41st International Conference on Machine Learning</i>, vol. 235, ML Research Press, 2024, pp. 35910–33."},"date_created":"2025-01-30T07:53:22Z","month":"07","external_id":{"arxiv":["2306.06098"]},"author":[{"id":"449f7a18-f128-11eb-9611-9b430c0c6333","last_name":"Modoranu","first_name":"Ionut-Vlad","full_name":"Modoranu, Ionut-Vlad"},{"orcid":"0000-0003-2189-3904","full_name":"Kalinov, Aleksei","first_name":"Aleksei","id":"44b7120e-eb97-11eb-a6c2-e1557aa81d02","last_name":"Kalinov"},{"first_name":"Eldar","last_name":"Kurtic","id":"47beb3a5-07b5-11eb-9b87-b108ec578218","full_name":"Kurtic, Eldar"},{"full_name":"Frantar, Elias","first_name":"Elias","id":"09a8f98d-ec99-11ea-ae11-c063a7b7fe5f","last_name":"Frantar"},{"full_name":"Alistarh, Dan-Adrian","orcid":"0000-0003-3650-940X","last_name":"Alistarh","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","first_name":"Dan-Adrian"}],"conference":{"name":"ICML: International Conference on Machine Learning","end_date":"2024-07-27","location":"Vienna, Austria","start_date":"2024-07-21"},"oa":1},{"oa_version":"Preprint","publication_status":"published","type":"conference","publisher":"OpenReview","scopus_import":"1","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2306.03078","open_access":"1"}],"publication":"12th International Conference on Learning Representations","researchdata_availability":"no","abstract":[{"text":"Recent advances in large language model (LLM) pretraining have led to high-quality LLMs with impressive abilities. By compressing such LLMs via quantization to 3-4 bits per parameter, they can fit into memory-limited devices such as laptops and mobile phones, enabling personalized use. Quantizing models to 3-4 bits per parameter can lead to moderate to high accuracy losses, especially for smaller models (1-10B parameters), which are suitable for edge deployment. To address this accuracy issue, we introduce the Sparse-Quantized Representation (SpQR), a new compressed format and quantization technique that enables for the first time \\emph{near-lossless} compression of LLMs across model scales while reaching similar compression levels to previous methods. SpQR works by identifying and isolating \\emph{outlier weights}, which cause particularly large quantization errors, and storing them in higher precision while compressing all other weights to 3-4 bits, and achieves relative accuracy losses of less than \r\n in perplexity for highly-accurate LLaMA and Falcon LLMs. This makes it possible to run a 33B parameter LLM on a single 24 GB consumer GPU without performance degradation at 15% speedup, thus making powerful LLMs available to consumers without any downsides. SpQR comes with efficient algorithms for both encoding weights into its format, as well as decoding them efficiently at runtime. Specifically, we provide an efficient GPU inference algorithm for SpQR, which yields faster inference than 16-bit baselines at similar accuracy while enabling memory compression gains of more than 4x.","lang":"eng"}],"quality_controlled":"1","article_processing_charge":"No","acknowledgement":"Denis Kuznedelev acknowledges the support from the Russian Ministry of Science and Higher\r\nEducation, grant No. 075-10-2021-068. Ruslan Svirschevski and Vage Egiazarian and Denis\r\nKuznedelev were supported by the grant for research centers in the field of AI provided by the\r\nAnalytical Center for the Government of the Russian Federation (ACRF) in accordance with the\r\nagreement on the provision of subsidies (identifier of the agreement 000000D730321P5Q0002) and the agreement with HSE University No. 70-2021-00139.","language":[{"iso":"eng"}],"_id":"18977","day":"15","title":"SpQR: A sparse-quantized representation for near-lossless LLM weight compression","arxiv":1,"date_published":"2024-05-15T00:00:00Z","date_updated":"2026-10-01T09:33:44Z","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","OA_place":"repository","das_tickbox":"0","supplementarymaterial":"no","oa":1,"author":[{"full_name":"Dettmers, Tim","last_name":"Dettmers","first_name":"Tim"},{"last_name":"Svirschevski","first_name":"Ruslan A.","full_name":"Svirschevski, Ruslan A."},{"last_name":"Egiazarian","first_name":"Vage","full_name":"Egiazarian, Vage"},{"last_name":"Kuznedelev","first_name":"Denis","full_name":"Kuznedelev, Denis"},{"id":"09a8f98d-ec99-11ea-ae11-c063a7b7fe5f","last_name":"Frantar","first_name":"Elias","full_name":"Frantar, Elias"},{"first_name":"Saleh","last_name":"Ashkboos","full_name":"Ashkboos, Saleh"},{"last_name":"Borzunov","first_name":"Alexander","full_name":"Borzunov, Alexander"},{"full_name":"Hoefler, Torsten","first_name":"Torsten","last_name":"Hoefler"},{"first_name":"Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","last_name":"Alistarh","full_name":"Alistarh, Dan-Adrian","orcid":"0000-0003-3650-940X"}],"conference":{"end_date":"2024-05-11","name":"ICLR: International Conference on Learning Representations","location":"Vienna, Austria","start_date":"2024-05-07"},"external_id":{"arxiv":["2306.03078"]},"month":"05","OA_type":"green","year":"2024","date_created":"2025-01-30T08:26:59Z","citation":{"ama":"Dettmers T, Svirschevski RA, Egiazarian V, et al. SpQR: A sparse-quantized representation for near-lossless LLM weight compression. In: <i>12th International Conference on Learning Representations</i>. OpenReview; 2024.","apa":"Dettmers, T., Svirschevski, R. A., Egiazarian, V., Kuznedelev, D., Frantar, E., Ashkboos, S., … Alistarh, D.-A. (2024). SpQR: A sparse-quantized representation for near-lossless LLM weight compression. In <i>12th International Conference on Learning Representations</i>. Vienna, Austria: OpenReview.","short":"T. Dettmers, R.A. Svirschevski, V. Egiazarian, D. Kuznedelev, E. Frantar, S. Ashkboos, A. Borzunov, T. Hoefler, D.-A. Alistarh, in:, 12th International Conference on Learning Representations, OpenReview, 2024.","mla":"Dettmers, Tim, et al. “SpQR: A Sparse-Quantized Representation for near-Lossless LLM Weight Compression.” <i>12th International Conference on Learning Representations</i>, OpenReview, 2024.","ista":"Dettmers T, Svirschevski RA, Egiazarian V, Kuznedelev D, Frantar E, Ashkboos S, Borzunov A, Hoefler T, Alistarh D-A. 2024. SpQR: A sparse-quantized representation for near-lossless LLM weight compression. 12th International Conference on Learning Representations. ICLR: International Conference on Learning Representations.","chicago":"Dettmers, Tim, Ruslan A. Svirschevski, Vage Egiazarian, Denis Kuznedelev, Elias Frantar, Saleh Ashkboos, Alexander Borzunov, Torsten Hoefler, and Dan-Adrian Alistarh. “SpQR: A Sparse-Quantized Representation for near-Lossless LLM Weight Compression.” In <i>12th International Conference on Learning Representations</i>. OpenReview, 2024.","ieee":"T. Dettmers <i>et al.</i>, “SpQR: A sparse-quantized representation for near-lossless LLM weight compression,” in <i>12th International Conference on Learning Representations</i>, Vienna, Austria, 2024."},"department":[{"_id":"DaAl"}],"status":"public"},{"oa_version":"Preprint","publication_status":"published","corr_author":"1","alternative_title":["PMLR"],"volume":238,"page":"3448-3456","type":"conference","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2206.10032","open_access":"1"}],"scopus_import":"1","publisher":"ML Research Press","abstract":[{"text":"Federated Learning (FL) enables large-scale distributed training of machine learning models, while still allowing individual nodes to maintain data locally. However, executing FL at scale comes with inherent practical challenges: 1) heterogeneity of the local node data distributions, 2) heterogeneity of node computational speeds (asynchrony), but also 3) constraints in the amount of communication between the clients and the server. In this work, we present the first variant of the classic federated averaging (FedAvg) algorithm which, at the same time, supports data heterogeneity, partial client asynchrony, and communication compression. Our algorithm comes with a novel, rigorous analysis showing that, in spite of these system relaxations, it can provide similar convergence to FedAvg in interesting parameter regimes. Experimental results in the rigorous LEAF benchmark on setups of up to 300 nodes show that our algorithm ensures fast convergence for standard federated tasks, improving upon prior quantized and asynchronous approaches.","lang":"eng"}],"publication":"Proceedings of the 27th International Conference on Artificial Intelligence and Statistics","researchdata_availability":"no","article_processing_charge":"No","quality_controlled":"1","day":"01","language":[{"iso":"eng"}],"_id":"17093","arxiv":1,"title":"Communication-efficient federated learning with data and client heterogeneity","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","date_published":"2024-05-01T00:00:00Z","date_updated":"2026-10-01T09:34:02Z","publication_identifier":{"eissn":["2640-3498"]},"supplementarymaterial":"no","intvolume":"       238","das_tickbox":"0","author":[{"id":"653bd8b6-f394-11eb-9cf6-c0bbf6cd78d4","last_name":"Zakerinia","first_name":"Hossein","orcid":"0009-0007-3977-6462","full_name":"Zakerinia, Hossein"},{"last_name":"Talaei","first_name":"Shayan","full_name":"Talaei, Shayan"},{"id":"3279A00C-F248-11E8-B48F-1D18A9856A87","last_name":"Nadiradze","first_name":"Giorgi","full_name":"Nadiradze, Giorgi","orcid":"0000-0001-5634-0731"},{"full_name":"Alistarh, Dan-Adrian","orcid":"0000-0003-3650-940X","last_name":"Alistarh","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","first_name":"Dan-Adrian"}],"conference":{"name":"AISTATS: Conference on Artificial Intelligence and Statistics","end_date":"2024-05-04","location":"Valencia, Spain","start_date":"2024-05-02"},"oa":1,"month":"05","external_id":{"arxiv":["2206.10032"]},"department":[{"_id":"DaAl"},{"_id":"ChLa"}],"year":"2024","citation":{"mla":"Zakerinia, Hossein, et al. “Communication-Efficient Federated Learning with Data and Client Heterogeneity.” <i>Proceedings of the 27th International Conference on Artificial Intelligence and Statistics</i>, vol. 238, ML Research Press, 2024, pp. 3448–56.","short":"H. Zakerinia, S. Talaei, G. Nadiradze, D.-A. Alistarh, in:, Proceedings of the 27th International Conference on Artificial Intelligence and Statistics, ML Research Press, 2024, pp. 3448–3456.","apa":"Zakerinia, H., Talaei, S., Nadiradze, G., &#38; Alistarh, D.-A. (2024). Communication-efficient federated learning with data and client heterogeneity. In <i>Proceedings of the 27th International Conference on Artificial Intelligence and Statistics</i> (Vol. 238, pp. 3448–3456). Valencia, Spain: ML Research Press.","ama":"Zakerinia H, Talaei S, Nadiradze G, Alistarh D-A. Communication-efficient federated learning with data and client heterogeneity. In: <i>Proceedings of the 27th International Conference on Artificial Intelligence and Statistics</i>. Vol 238. ML Research Press; 2024:3448-3456.","ieee":"H. Zakerinia, S. Talaei, G. Nadiradze, and D.-A. Alistarh, “Communication-efficient federated learning with data and client heterogeneity,” in <i>Proceedings of the 27th International Conference on Artificial Intelligence and Statistics</i>, Valencia, Spain, 2024, vol. 238, pp. 3448–3456.","chicago":"Zakerinia, Hossein, Shayan Talaei, Giorgi Nadiradze, and Dan-Adrian Alistarh. “Communication-Efficient Federated Learning with Data and Client Heterogeneity.” In <i>Proceedings of the 27th International Conference on Artificial Intelligence and Statistics</i>, 238:3448–56. ML Research Press, 2024.","ista":"Zakerinia H, Talaei S, Nadiradze G, Alistarh D-A. 2024. Communication-efficient federated learning with data and client heterogeneity. Proceedings of the 27th International Conference on Artificial Intelligence and Statistics. AISTATS: Conference on Artificial Intelligence and Statistics, PMLR, vol. 238, 3448–3456."},"date_created":"2024-06-02T22:00:57Z","status":"public"}]