[{"isi":1,"fulldoi":"https://doi.org/10.1145/3658194","project":[{"_id":"34bc2376-11ca-11ed-8bc3-9a3b3961a088","name":"Computational Discovery of Numerical Algorithms for Animation and Simulation of Natural Phenomena","grant_number":"101045083"}],"oa_version":"Published Version","date_published":"2024-07-01T00:00:00Z","abstract":[{"lang":"eng","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."}],"intvolume":"        43","author":[{"id":"400429CC-F248-11E8-B48F-1D18A9856A87","full_name":"Hafner, Christian","last_name":"Hafner","first_name":"Christian"},{"first_name":"Mickaël","last_name":"Ly","id":"6340d7f0-b48d-11eb-b10d-b7487e71d9f1","full_name":"Ly, Mickaël"},{"orcid":"0000-0001-6646-5546","first_name":"Christopher J","id":"3C61F1D2-F248-11E8-B48F-1D18A9856A87","full_name":"Wojtan, Christopher J","last_name":"Wojtan"}],"issue":"4","publication_status":"published","researchdata_availability":"no","quality_controlled":"1","doi":"10.1145/3658194","conference":{"location":"Denver, Colorado","start_date":"2024-07-28","end_date":"2024-08-01"},"keyword":["Topology Optimization","Mass Moments","Computational Geometry"],"year":"2024","_id":"17203","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","status":"public","article_processing_charge":"Yes (via OA deal)","external_id":{"isi":["001289270900045"]},"citation":{"short":"C. Hafner, M. Ly, C. Wojtan, Transactions on Graphics 43 (2024).","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>.","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>.","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>","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.","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.","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>"},"article_number":"78","publication":"Transactions on Graphics","date_created":"2024-07-05T12:08:57Z","article_type":"original","volume":43,"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).","supplementarymaterial":"yes","type":"journal_article","ddc":["516"],"month":"07","file":[{"file_id":"17204","file_size":7225150,"checksum":"0dc9f5a6422b8a49a79026900f349ee5","content_type":"application/pdf","relation":"main_file","file_name":"sif-final.pdf","creator":"chafner","success":1,"date_updated":"2024-07-05T12:05:17Z","access_level":"open_access","date_created":"2024-07-05T12:05:17Z"},{"relation":"supplementary_material","content_type":"application/pdf","checksum":"cde433c6a40688d5f1187fb5721f6f94","file_size":397262,"file_id":"17205","date_created":"2024-07-05T12:06:03Z","access_level":"open_access","date_updated":"2024-07-05T12:06:03Z","creator":"chafner","file_name":"sif-supp-final.pdf"},{"file_id":"17276","file_size":170001305,"checksum":"c0457a09c2ab9a1c2935c995dcc84907","content_type":"video/mp4","relation":"supplementary_material","file_name":"sif-video-final.mp4","title":"Submission Video","creator":"chafner","date_updated":"2024-07-17T09:29:13Z","access_level":"open_access","date_created":"2024-07-17T09:29:13Z"}],"department":[{"_id":"ChWo"}],"language":[{"iso":"eng"}],"has_accepted_license":"1","corr_author":"1","scopus_import":"1","file_date_updated":"2024-07-17T09:29:13Z","publication_identifier":{"issn":["0730-0301"],"eissn":["1557-7368"]},"publisher":"Association for Computing Machinery","date_updated":"2026-10-01T09:30:01Z","das_tickbox":"0","title":"Spin-it faster: Quadrics solve all topology optimization problems that depend only on mass moments","oa":1,"day":"01"},{"das_tickbox":"1","title":"Dynamics and scaling of internally cooled convection","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"},"date_updated":"2026-10-01T09:27:13Z","day":"01","oa":1,"file":[{"content_type":"application/pdf","relation":"main_file","file_size":1257925,"file_id":"18795","checksum":"9b7c2b8281d0b7bc7f08e0468168324c","success":1,"date_updated":"2025-01-09T09:05:31Z","date_created":"2025-01-09T09:05:31Z","access_level":"open_access","file_name":"2024_CommNonlinear_Agasthya.pdf","creator":"dernst"}],"dataavailabilitystatement":"Data will be made available on request","department":[{"_id":"CaMu"}],"language":[{"iso":"eng"}],"arxiv":1,"date_created":"2024-04-14T22:01:01Z","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).","article_type":"original","volume":134,"ddc":["550"],"month":"07","supplementarymaterial":"no","type":"journal_article","ec_funded":1,"publication_identifier":{"issn":["1007-5704"]},"publisher":"Elsevier","has_accepted_license":"1","acknowledged_ssus":[{"_id":"ScienComp"}],"corr_author":"1","scopus_import":"1","OA_place":"publisher","file_date_updated":"2025-01-09T09:05:31Z","OA_type":"hybrid","_id":"15313","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","status":"public","year":"2024","article_number":"108011","publication":"Communications in Nonlinear Science and Numerical Simulation","article_processing_charge":"Yes (via OA deal)","external_id":{"arxiv":["2311.04114"],"isi":["001238294600001"]},"citation":{"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>","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.","ista":"Agasthya LN, Muller CJ. 2024. Dynamics and scaling of internally cooled convection. Communications in Nonlinear Science and Numerical Simulation. 134, 108011.","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>","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>.","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>.","short":"L.N. Agasthya, C.J. Muller, Communications in Nonlinear Science and Numerical Simulation 134 (2024)."},"intvolume":"       134","abstract":[{"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.","lang":"eng"}],"publication_status":"published","author":[{"full_name":"Agasthya, Lokahith N","id":"cd100965-0804-11ed-9c55-f4878ff4e877","last_name":"Agasthya","first_name":"Lokahith N"},{"full_name":"Muller, Caroline J","id":"f978ccb0-3f7f-11eb-b193-b0e2bd13182b","last_name":"Muller","orcid":"0000-0001-5836-5350","first_name":"Caroline J"}],"fulldoi":"https://doi.org/10.1016/j.cnsns.2024.108011","oa_version":"Published Version","date_published":"2024-07-01T00:00:00Z","isi":1,"project":[{"_id":"fc2ed2f7-9c52-11eb-aca3-c01059dda49c","call_identifier":"H2020","grant_number":"101034413","name":"IST-BRIDGE: International postdoctoral program"},{"_id":"629205d8-2b32-11ec-9570-e1356ff73576","call_identifier":"H2020","name":"Organization of CLoUdS, and implications of Tropical  cyclones and for the Energetics of the tropics, in current and waRming climate","grant_number":"805041"}],"quality_controlled":"1","doi":"10.1016/j.cnsns.2024.108011","researchdata_availability":"upon request"},{"author":[{"first_name":"Jonathan A","last_name":"Scott","full_name":"Scott, Jonathan A","id":"e499926b-f6e0-11ea-865d-9c63db0031e8"},{"last_name":"Zakerinia","id":"653bd8b6-f394-11eb-9cf6-c0bbf6cd78d4","full_name":"Zakerinia, Hossein","first_name":"Hossein","orcid":"0009-0007-3977-6462"},{"last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph","first_name":"Christoph","orcid":"0000-0001-8622-7887"}],"publication_status":"published","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"}],"oa_version":"Published Version","date_published":"2024-03-07T00:00:00Z","quality_controlled":"1","conference":{"end_date":"2024-03-07","location":"Vienna, Austria","name":"ICLR: International Conference on Learning Representations","start_date":"2024-03-07"},"researchdata_availability":"no","_id":"17411","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","status":"public","year":"2024","publication":"12th International Conference on Learning Representations","citation":{"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.","mla":"Scott, Jonathan A., et al. “PEFLL: Personalized Federated Learning by Learning to Learn.” <i>12th International Conference on Learning Representations</i>, OpenReview, 2024.","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.","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.","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.","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."},"article_processing_charge":"No","external_id":{"arxiv":["2306.05515"]},"department":[{"_id":"ChLa"}],"language":[{"iso":"eng"}],"arxiv":1,"file":[{"creator":"dernst","file_name":"2024_ICLR_Scott.pdf","date_created":"2024-08-12T07:38:06Z","access_level":"open_access","date_updated":"2024-08-12T07:38:06Z","success":1,"checksum":"81b7ea2e667adaf9c7a7b6b376b1f251","file_id":"17415","file_size":1029219,"relation":"main_file","content_type":"application/pdf"}],"month":"03","type":"conference","ddc":["000"],"supplementarymaterial":"no","date_created":"2024-08-11T22:01:12Z","acknowledgement":"This research was supported by the Scientific Service Units (SSU) of ISTA through resources provided by Scientific Computing (SciComp).\r\n","publisher":"OpenReview","acknowledged_ssus":[{"_id":"ScienComp"}],"corr_author":"1","file_date_updated":"2024-08-12T07:38:06Z","scopus_import":"1","has_accepted_license":"1","title":"PEFLL: Personalized federated learning by learning to learn","das_tickbox":"0","date_updated":"2026-10-01T09:28:03Z","day":"07","related_material":{"record":[{"status":"public","relation":"dissertation_contains","id":"21198"}]},"oa":1},{"publisher":"ML Research Press","publication_identifier":{"eissn":["2640-3498"]},"scopus_import":"1","corr_author":"1","alternative_title":["PMLR"],"language":[{"iso":"eng"}],"arxiv":1,"main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2406.02416","open_access":"1"}],"department":[{"_id":"ChLa"}],"supplementarymaterial":"no","type":"conference","month":"09","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.","volume":235,"page":"44012-44037","date_created":"2024-09-22T22:01:45Z","day":"01","related_material":{"record":[{"id":"21198","relation":"dissertation_contains","status":"public"}]},"oa":1,"title":"Improved modelling of federated datasets using mixtures-of-Dirichlet-multinomials","das_tickbox":"0","date_updated":"2026-10-01T09:29:04Z","conference":{"end_date":"2024-07-27","location":"Vienna, Austria","name":"ICML: International Conference on Machine Learning","start_date":"2024-07-21"},"quality_controlled":"1","researchdata_availability":"no","author":[{"id":"e499926b-f6e0-11ea-865d-9c63db0031e8","full_name":"Scott, Jonathan A","last_name":"Scott","first_name":"Jonathan A"},{"last_name":"Cahill","full_name":"Cahill, Áine","first_name":"Áine"}],"publication_status":"published","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"}],"intvolume":"       235","oa_version":"Preprint","date_published":"2024-09-01T00:00:00Z","publication":"Proceedings of the 41st International Conference on Machine Learning","citation":{"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.","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.","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.","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.","short":"J.A. Scott, Á. Cahill, in:, Proceedings of the 41st International Conference on Machine Learning, ML Research Press, 2024, 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.","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."},"external_id":{"arxiv":["2406.02416"]},"article_processing_charge":"No","status":"public","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","_id":"18120","year":"2024"},{"oa":1,"day":"01","date_updated":"2026-10-01T09:28:21Z","das_tickbox":"0","title":"More flexible PAC-Bayesian meta-learning by learning learning algorithms","alternative_title":["PMLR"],"corr_author":"1","scopus_import":"1","publication_identifier":{"eissn":["2640-3498"]},"publisher":"ML Research Press","date_created":"2024-09-22T22:01:45Z","page":"58122-58139","volume":235,"month":"09","type":"conference","supplementarymaterial":"no","ddc":["000"],"department":[{"_id":"ChLa"}],"main_file_link":[{"open_access":"1","url":" https://doi.org/10.48550/arXiv.2402.04054"}],"arxiv":1,"language":[{"iso":"eng"}],"article_processing_charge":"No","external_id":{"arxiv":["2402.04054"]},"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.","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.","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.","short":"H. Zakerinia, A. Behjati, C. Lampert, in:, Proceedings of the 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 58122–58139."},"publication":"Proceedings of the 41st International Conference on Machine Learning","year":"2024","_id":"18118","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","status":"public","researchdata_availability":"no","quality_controlled":"1","conference":{"end_date":"2024-07-27","location":"Vienna, Austria","name":"ICML: International Conference on Machine Learning","start_date":"2024-07-21"},"date_published":"2024-09-01T00:00:00Z","oa_version":"Published Version","abstract":[{"lang":"eng","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."}],"intvolume":"       235","author":[{"orcid":"0009-0007-3977-6462","first_name":"Hossein","id":"653bd8b6-f394-11eb-9cf6-c0bbf6cd78d4","full_name":"Zakerinia, Hossein","last_name":"Zakerinia"},{"full_name":"Behjati, Amin","last_name":"Behjati","first_name":"Amin"},{"last_name":"Lampert","full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","first_name":"Christoph","orcid":"0000-0001-8622-7887"}],"publication_status":"published"},{"publication":"2024 IEEE International Parallel and Distributed Processing Symposium","external_id":{"arxiv":["2310.05293"],"isi":["001270389600078"]},"article_processing_charge":"No","citation":{"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>","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.","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>","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.","short":"I. Kokorin, V. Yudov, V. Aksenov, D.-A. Alistarh, in:, 2024 IEEE International Parallel and Distributed Processing Symposium, IEEE, 2024, pp. 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>.","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>."},"user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","status":"public","_id":"17332","year":"2024","doi":"10.1109/IPDPS57955.2024.00023","conference":{"name":"IPDPS: International Parallel and Distributed Processing Symposium","start_date":"2024-05-27","location":"San Francisco, CA, United States","end_date":"2024-05-31"},"quality_controlled":"1","researchdata_availability":"no","abstract":[{"lang":"eng","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."}],"author":[{"first_name":"Ilya","full_name":"Kokorin, Ilya","last_name":"Kokorin"},{"first_name":"Victor","last_name":"Yudov","full_name":"Yudov, Victor"},{"last_name":"Aksenov","full_name":"Aksenov, Vitaly","first_name":"Vitaly"},{"first_name":"Dan-Adrian","orcid":"0000-0003-3650-940X","last_name":"Alistarh","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","full_name":"Alistarh, Dan-Adrian"}],"publication_status":"published","fulldoi":"https://doi.org/10.1109/IPDPS57955.2024.00023","oa_version":"Preprint","isi":1,"date_published":"2024-07-08T00:00:00Z","day":"08","oa":1,"das_tickbox":"0","title":"Wait-free trees with asymptotically-efficient range queries","date_updated":"2026-10-01T09:30:18Z","publication_identifier":{"isbn":["9798350337662"],"eissn":["1530-2075"]},"publisher":"IEEE","scopus_import":"1","corr_author":"1","language":[{"iso":"eng"}],"arxiv":1,"main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2310.05293"}],"department":[{"_id":"DaAl"}],"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.","page":"169-179","date_created":"2024-07-28T22:01:11Z","month":"07","type":"conference","supplementarymaterial":"no"},{"day":"08","oa":1,"title":"How to prune your language model: Recovering accuracy on the \"Sparsity May Cry\" benchmark","das_tickbox":"0","date_updated":"2026-10-01T09:31:02Z","publisher":"ML Research Press","publication_identifier":{"eissn":["2640-3498"]},"scopus_import":"1","corr_author":"1","alternative_title":["PMLR"],"language":[{"iso":"eng"}],"arxiv":1,"main_file_link":[{"open_access":"1","url":"https://proceedings.mlr.press/v234/kurtic24a"}],"department":[{"_id":"DaAl"}],"type":"conference","supplementarymaterial":"no","month":"01","volume":234,"page":"542-553","date_created":"2024-02-18T23:01:03Z","publication":"Proceedings of Machine Learning Research","citation":{"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.","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.","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.","short":"E. Kurtic, T. Hoefler, D.-A. Alistarh, in:, Proceedings of Machine Learning Research, ML Research Press, 2024, pp. 542–553.","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.","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."},"external_id":{"arxiv":["2312.13547"]},"article_processing_charge":"No","status":"public","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","_id":"15011","year":"2024","conference":{"end_date":"2024-01-06","location":"Hongkong, China","name":"CPAL: Conference on Parsimony and Learning","start_date":"2024-01-03"},"quality_controlled":"1","researchdata_availability":"no","publication_status":"published","author":[{"id":"47beb3a5-07b5-11eb-9b87-b108ec578218","full_name":"Kurtic, Eldar","last_name":"Kurtic","first_name":"Eldar"},{"first_name":"Torsten","full_name":"Hoefler, Torsten","last_name":"Hoefler"},{"first_name":"Dan-Adrian","orcid":"0000-0003-3650-940X","last_name":"Alistarh","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","full_name":"Alistarh, Dan-Adrian"}],"intvolume":"       234","abstract":[{"lang":"eng","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."}],"oa_version":"Preprint","date_published":"2024-01-08T00:00:00Z"},{"article_processing_charge":"No","external_id":{"isi":["001304430200075"]},"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>.","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>.","short":"B. Chatterjee, V. Kungurtsev, D.-A. Alistarh, in:, Proceedings of the 44th International Conference on Distributed Computing Systems, IEEE, 2024, pp. 857–868.","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.","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.","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>","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>"},"publication":"Proceedings of the 44th International Conference on Distributed Computing Systems","year":"2024","_id":"18070","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","status":"public","researchdata_availability":"yes","quality_controlled":"1","doi":"10.1109/ICDCS60910.2024.00084","conference":{"name":"ICDCS: International Conference on Distributed Computing Systems","start_date":"2024-07-23","location":"Jersey City, NJ, United States","end_date":"2024-07-26"},"fulldoi":"https://doi.org/10.1109/ICDCS60910.2024.00084","isi":1,"oa_version":"None","date_published":"2024-07-26T00:00:00Z","abstract":[{"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.","lang":"eng"}],"publication_status":"published","author":[{"first_name":"Bapi","orcid":"0000-0002-2742-4028","last_name":"Chatterjee","id":"3C41A08A-F248-11E8-B48F-1D18A9856A87","full_name":"Chatterjee, Bapi"},{"first_name":"Vyacheslav","full_name":"Kungurtsev, Vyacheslav","last_name":"Kungurtsev"},{"id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","full_name":"Alistarh, Dan-Adrian","last_name":"Alistarh","orcid":"0000-0003-3650-940X","first_name":"Dan-Adrian"}],"day":"26","date_updated":"2026-10-01T09:32:24Z","das_tickbox":"0","title":"Federated SGD with local asynchrony","corr_author":"1","scopus_import":"1","publication_identifier":{"eissn":["2575-8411"],"issn":["1063-6927"],"isbn":["9798350386059"]},"publisher":"IEEE","date_created":"2024-09-15T22:01:41Z","page":"857-868","supplementarymaterial":"no","month":"07","type":"conference","department":[{"_id":"DaAl"}],"language":[{"iso":"eng"}]},{"file":[{"date_created":"2024-07-29T07:37:31Z","access_level":"open_access","date_updated":"2024-07-29T07:37:31Z","success":1,"creator":"dernst","file_name":"2024_ACMPODC_Alistarh.pdf","relation":"main_file","content_type":"application/pdf","checksum":"65a40437f83373fa79dd999d5287509e","file_id":"17335","file_size":750908}],"department":[{"_id":"DaAl"},{"_id":"KrCh"}],"language":[{"iso":"eng"}],"page":"40-49","date_created":"2024-07-28T22:01:10Z","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.","supplementarymaterial":"no","month":"06","ddc":["000"],"type":"conference","ec_funded":1,"publication_identifier":{"isbn":["9798400706684"]},"publisher":"Association for Computing Machinery","has_accepted_license":"1","corr_author":"1","scopus_import":"1","file_date_updated":"2024-07-29T07:37:31Z","das_tickbox":"0","title":"Game dynamics and equilibrium computation in the population protocol model","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"},"date_updated":"2026-10-01T09:34:57Z","day":"17","oa":1,"abstract":[{"lang":"eng","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."}],"publication_status":"published","author":[{"orcid":"0000-0003-3650-940X","first_name":"Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","full_name":"Alistarh, Dan-Adrian","last_name":"Alistarh"},{"first_name":"Krishnendu","orcid":"0000-0002-4561-241X","last_name":"Chatterjee","id":"2E5DCA20-F248-11E8-B48F-1D18A9856A87","full_name":"Chatterjee, Krishnendu"},{"orcid":"0009-0007-5253-9170","first_name":"Mehrdad","full_name":"Karrabi, Mehrdad","id":"67638922-f394-11eb-9cf6-f20423e08757","last_name":"Karrabi"},{"last_name":"Lazarsfeld","id":"17ce3656-183e-11ef-84c3-8932383e1b23","full_name":"Lazarsfeld, John M","first_name":"John M"}],"oa_version":"Published Version","fulldoi":"https://doi.org/10.1145/3662158.3662768","date_published":"2024-06-17T00:00:00Z","project":[{"_id":"0599E47C-7A3F-11EA-A408-12923DDC885E","call_identifier":"H2020","grant_number":"863818","name":"Formal Methods for Stochastic Models: Algorithms and Applications"}],"quality_controlled":"1","doi":"10.1145/3662158.3662768","conference":{"end_date":"2024-06-21","location":"Nantes, France","start_date":"2024-06-17","name":"PODC: Symposium on Principles of Distributed Computing"},"researchdata_availability":"no","_id":"17329","status":"public","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","year":"2024","publication":"Proceedings of the 43rd Annual ACM Symposium on Principles of Distributed Computing","article_processing_charge":"Yes (via OA deal)","citation":{"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>","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.","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>.","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>.","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.","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.","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>"}},{"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.","volume":235,"date_created":"2024-09-22T22:01:46Z","page":"45955-45987","month":"09","type":"conference","supplementarymaterial":"no","arxiv":1,"language":[{"iso":"eng"}],"main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2310.04519"}],"department":[{"_id":"DaAl"}],"alternative_title":["PMLR"],"scopus_import":"1","acknowledged_ssus":[{"_id":"ScienComp"}],"corr_author":"1","publication_identifier":{"eissn":["2640-3498"]},"publisher":"ML Research Press","date_updated":"2026-10-01T09:32:47Z","das_tickbox":"0","title":"SPADE: Sparsity-guided debugging for deep neural networks","oa":1,"related_material":{"record":[{"status":"public","id":"21854","relation":"dissertation_contains"}],"link":[{"url":"https://github.com/IST-DASLab/SPADE","relation":"software"}]},"day":"01","oa_version":"Preprint","project":[{"grant_number":"W1260-N35","name":"Vienna Graduate School on Computational Optimization","_id":"9B9290DE-BA93-11EA-9121-9846C619BF3A"}],"date_published":"2024-09-01T00:00:00Z","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"}],"intvolume":"       235","author":[{"first_name":"Arshia Soltani","last_name":"Moakhar","full_name":"Moakhar, Arshia Soltani"},{"first_name":"Eugenia B","orcid":"0000-0002-7778-3221","last_name":"Iofinova","id":"f9a17499-f6e0-11ea-865d-fdf9a3f77117","full_name":"Iofinova, Eugenia B"},{"first_name":"Elias","full_name":"Frantar, Elias","id":"09a8f98d-ec99-11ea-ae11-c063a7b7fe5f","last_name":"Frantar"},{"orcid":"0000-0003-3650-940X","first_name":"Dan-Adrian","full_name":"Alistarh, Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","last_name":"Alistarh"}],"publication_status":"published","researchdata_availability":"yes","conference":{"location":"Vienna, Austria","start_date":"2024-07-21","name":"ICML: International Conference on Machine Learning","end_date":"2024-07-27"},"quality_controlled":"1","year":"2024","status":"public","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","_id":"18121","external_id":{"arxiv":["2310.04519"]},"article_processing_charge":"No","citation":{"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.","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.","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.","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.","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.","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.","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."},"publication":"Proceedings of the 41st International Conference on Machine Learning"},{"arxiv":1,"language":[{"iso":"eng"}],"main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2310.20452","open_access":"1"}],"department":[{"_id":"DaAl"}],"month":"05","supplementarymaterial":"no","type":"conference","volume":238,"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.","date_created":"2025-01-30T08:15:49Z","page":"649-657","publisher":"ML Research Press","publication_identifier":{"eissn":["2640-3498"]},"ec_funded":1,"OA_place":"repository","scopus_import":"1","corr_author":"1","alternative_title":["PMLR"],"title":"AsGrad: A sharp unified analysis of asynchronous-SGD algorithms","das_tickbox":"0","date_updated":"2026-10-01T09:33:24Z","day":"15","oa":1,"publication_status":"published","author":[{"full_name":"Islamov, Rustem","last_name":"Islamov","first_name":"Rustem"},{"first_name":"Mher","full_name":"Safaryan, Mher","id":"dd546b39-0804-11ed-9c55-ef075c39778d","last_name":"Safaryan"},{"full_name":"Alistarh, Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","last_name":"Alistarh","orcid":"0000-0003-3650-940X","first_name":"Dan-Adrian"}],"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."}],"intvolume":"       238","oa_version":"Preprint","date_published":"2024-05-15T00:00:00Z","project":[{"call_identifier":"H2020","_id":"fc2ed2f7-9c52-11eb-aca3-c01059dda49c","grant_number":"101034413","name":"IST-BRIDGE: International postdoctoral program"}],"conference":{"end_date":"2024-05-04","location":"Valencia, Spain","name":"AISTATS: Conference on Artificial Intelligence and Statistics","start_date":"2024-05-02"},"quality_controlled":"1","researchdata_availability":"no","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","status":"public","_id":"18976","OA_type":"green","year":"2024","publication":"Proceedings of The 27th International Conference on Artificial Intelligence and Statistics","citation":{"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.","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.","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.","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.","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.","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.","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."},"external_id":{"arxiv":["2310.20452"]},"article_processing_charge":"No"},{"oa":1,"day":"01","date_updated":"2026-10-01T09:34:19Z","das_tickbox":"0","title":"Extreme compression of large language models via additive quantization","alternative_title":["PMLR"],"corr_author":"1","scopus_import":"1","publication_identifier":{"eissn":["2640-3498"]},"publisher":"ML Research Press","page":"12284-12303","date_created":"2024-09-22T22:01:43Z","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.","volume":235,"month":"09","type":"conference","supplementarymaterial":"no","main_file_link":[{"open_access":"1","url":" https://doi.org/10.48550/arXiv.2401.06118"}],"department":[{"_id":"DaAl"},{"_id":"GradSch"}],"language":[{"iso":"eng"}],"arxiv":1,"article_processing_charge":"No","external_id":{"arxiv":["2401.06118"]},"citation":{"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.","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.","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.","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.","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.","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.","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."},"publication":"Proceedings of the 41st International Conference on Machine Learning","year":"2024","_id":"18113","status":"public","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","researchdata_availability":"no","quality_controlled":"1","conference":{"end_date":"2024-07-27","start_date":"2024-07-21","name":"ICML: International Conference on Machine Learning","location":"Vienna, Austria"},"oa_version":"Preprint","date_published":"2024-09-01T00:00:00Z","intvolume":"       235","abstract":[{"lang":"eng","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."}],"author":[{"first_name":"Vage","full_name":"Egiazarian, Vage","last_name":"Egiazarian"},{"first_name":"Andrei","last_name":"Panferov","full_name":"Panferov, Andrei","id":"2c18daae-4dbe-11ef-8491-98ce2d960f09"},{"first_name":"Denis","full_name":"Kuznedelev, Denis","last_name":"Kuznedelev"},{"first_name":"Elias","full_name":"Frantar, Elias","id":"09a8f98d-ec99-11ea-ae11-c063a7b7fe5f","last_name":"Frantar"},{"first_name":"Artem","full_name":"Babenko, Artem","last_name":"Babenko"},{"first_name":"Dan-Adrian","orcid":"0000-0003-3650-940X","last_name":"Alistarh","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","full_name":"Alistarh, Dan-Adrian"}],"publication_status":"published"},{"publication_identifier":{"eissn":["2640-3498"]},"publisher":"ML Research Press","alternative_title":["PMLR"],"acknowledged_ssus":[{"_id":"CampIT"}],"corr_author":"1","OA_place":"repository","scopus_import":"1","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2306.06098","open_access":"1"}],"department":[{"_id":"DaAl"}],"language":[{"iso":"eng"}],"arxiv":1,"page":"35910-35933","date_created":"2025-01-30T07:53:22Z","volume":235,"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.","type":"conference","month":"07","supplementarymaterial":"no","day":"30","oa":1,"das_tickbox":"0","title":"Error feedback can accurately compress preconditioners","date_updated":"2026-10-01T09:33:07Z","quality_controlled":"1","conference":{"end_date":"2024-07-27","location":"Vienna, Austria","start_date":"2024-07-21","name":"ICML: International Conference on Machine Learning"},"researchdata_availability":"yes","intvolume":"       235","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."}],"author":[{"first_name":"Ionut-Vlad","full_name":"Modoranu, Ionut-Vlad","id":"449f7a18-f128-11eb-9611-9b430c0c6333","last_name":"Modoranu"},{"orcid":"0000-0003-2189-3904","first_name":"Aleksei","full_name":"Kalinov, Aleksei","id":"44b7120e-eb97-11eb-a6c2-e1557aa81d02","last_name":"Kalinov"},{"last_name":"Kurtic","full_name":"Kurtic, Eldar","id":"47beb3a5-07b5-11eb-9b87-b108ec578218","first_name":"Eldar"},{"last_name":"Frantar","id":"09a8f98d-ec99-11ea-ae11-c063a7b7fe5f","full_name":"Frantar, Elias","first_name":"Elias"},{"full_name":"Alistarh, Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","last_name":"Alistarh","orcid":"0000-0003-3650-940X","first_name":"Dan-Adrian"}],"publication_status":"published","date_published":"2024-07-30T00:00:00Z","oa_version":"Preprint","publication":"41st International Conference on Machine Learning","article_processing_charge":"No","external_id":{"arxiv":["2306.06098"]},"citation":{"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.","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.","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."},"OA_type":"green","_id":"18975","status":"public","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","year":"2024"},{"OA_place":"repository","scopus_import":"1","publisher":"OpenReview","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.","date_created":"2025-01-30T08:26:59Z","type":"conference","month":"05","supplementarymaterial":"no","arxiv":1,"language":[{"iso":"eng"}],"main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2306.03078","open_access":"1"}],"department":[{"_id":"DaAl"}],"oa":1,"day":"15","date_updated":"2026-10-01T09:33:44Z","das_tickbox":"0","title":"SpQR: A sparse-quantized representation for near-lossless LLM weight compression","researchdata_availability":"no","conference":{"location":"Vienna, Austria","name":"ICLR: International Conference on Learning Representations","start_date":"2024-05-07","end_date":"2024-05-11"},"quality_controlled":"1","oa_version":"Preprint","date_published":"2024-05-15T00:00:00Z","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"}],"publication_status":"published","author":[{"full_name":"Dettmers, Tim","last_name":"Dettmers","first_name":"Tim"},{"first_name":"Ruslan A.","full_name":"Svirschevski, Ruslan A.","last_name":"Svirschevski"},{"first_name":"Vage","full_name":"Egiazarian, Vage","last_name":"Egiazarian"},{"first_name":"Denis","last_name":"Kuznedelev","full_name":"Kuznedelev, Denis"},{"full_name":"Frantar, Elias","id":"09a8f98d-ec99-11ea-ae11-c063a7b7fe5f","last_name":"Frantar","first_name":"Elias"},{"first_name":"Saleh","full_name":"Ashkboos, Saleh","last_name":"Ashkboos"},{"first_name":"Alexander","last_name":"Borzunov","full_name":"Borzunov, Alexander"},{"first_name":"Torsten","full_name":"Hoefler, Torsten","last_name":"Hoefler"},{"orcid":"0000-0003-3650-940X","first_name":"Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","full_name":"Alistarh, Dan-Adrian","last_name":"Alistarh"}],"external_id":{"arxiv":["2306.03078"]},"article_processing_charge":"No","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.","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.","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.","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.","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.","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."},"publication":"12th International Conference on Learning Representations","year":"2024","OA_type":"green","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","status":"public","_id":"18977"},{"conference":{"start_date":"2024-05-02","name":"AISTATS: Conference on Artificial Intelligence and Statistics","location":"Valencia, Spain","end_date":"2024-05-04"},"quality_controlled":"1","researchdata_availability":"no","intvolume":"       238","abstract":[{"lang":"eng","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."}],"publication_status":"published","author":[{"first_name":"Hossein","orcid":"0009-0007-3977-6462","last_name":"Zakerinia","id":"653bd8b6-f394-11eb-9cf6-c0bbf6cd78d4","full_name":"Zakerinia, Hossein"},{"first_name":"Shayan","last_name":"Talaei","full_name":"Talaei, Shayan"},{"orcid":"0000-0001-5634-0731","first_name":"Giorgi","id":"3279A00C-F248-11E8-B48F-1D18A9856A87","full_name":"Nadiradze, Giorgi","last_name":"Nadiradze"},{"full_name":"Alistarh, Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","last_name":"Alistarh","orcid":"0000-0003-3650-940X","first_name":"Dan-Adrian"}],"date_published":"2024-05-01T00:00:00Z","oa_version":"Preprint","publication":"Proceedings of the 27th International Conference on Artificial Intelligence and Statistics","external_id":{"arxiv":["2206.10032"]},"article_processing_charge":"No","citation":{"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.","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.","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.","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.","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.","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.","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."},"status":"public","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","_id":"17093","year":"2024","publication_identifier":{"eissn":["2640-3498"]},"publisher":"ML Research Press","alternative_title":["PMLR"],"scopus_import":"1","corr_author":"1","language":[{"iso":"eng"}],"arxiv":1,"department":[{"_id":"DaAl"},{"_id":"ChLa"}],"main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2206.10032"}],"volume":238,"date_created":"2024-06-02T22:00:57Z","page":"3448-3456","type":"conference","supplementarymaterial":"no","month":"05","day":"01","oa":1,"das_tickbox":"0","title":"Communication-efficient federated learning with data and client heterogeneity","date_updated":"2026-10-01T09:34:02Z"},{"date_updated":"2026-10-01T09:34:36Z","das_tickbox":"0","title":"RoSA: Accurate parameter-efficient fine-tuning via robust adaptation","oa":1,"related_material":{"link":[{"relation":"software","url":"https://github.com/IST-DASLab/RoSA"}]},"day":"01","acknowledgement":"The authors would like to thank Eldar Kurtic for experimental support and useful suggestions throughout the project","volume":235,"page":"38187-38206","date_created":"2024-09-22T22:01:44Z","supplementarymaterial":"no","type":"conference","month":"09","arxiv":1,"language":[{"iso":"eng"}],"main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2401.04679"}],"department":[{"_id":"DaAl"},{"_id":"GradSch"}],"scopus_import":"1","corr_author":"1","publication_identifier":{"eissn":["2640-3498"]},"publisher":"ML Research Press","year":"2024","status":"public","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","_id":"18117","external_id":{"arxiv":["2401.04679"]},"article_processing_charge":"No","citation":{"ama":"Nikdan M, Tabesh S, Crncevic E, Alistarh D-A. RoSA: Accurate parameter-efficient fine-tuning via robust adaptation. In: <i>Proceedings of the 41st International Conference on Machine Learning</i>. Vol 235. ML Research Press; 2024:38187-38206.","mla":"Nikdan, Mahdi, et al. “RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation.” <i>Proceedings of the 41st International Conference on Machine Learning</i>, vol. 235, ML Research Press, 2024, pp. 38187–206.","chicago":"Nikdan, Mahdi, Soroush Tabesh, Elvir Crncevic, and Dan-Adrian Alistarh. “RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation.” In <i>Proceedings of the 41st International Conference on Machine Learning</i>, 235:38187–206. ML Research Press, 2024.","short":"M. Nikdan, S. Tabesh, E. Crncevic, D.-A. Alistarh, in:, Proceedings of the 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 38187–38206.","ieee":"M. Nikdan, S. Tabesh, E. Crncevic, and D.-A. Alistarh, “RoSA: Accurate parameter-efficient fine-tuning via robust adaptation,” in <i>Proceedings of the 41st International Conference on Machine Learning</i>, Vienna, Austria, 2024, vol. 235, pp. 38187–38206.","ista":"Nikdan M, Tabesh S, Crncevic E, Alistarh D-A. 2024. RoSA: Accurate parameter-efficient fine-tuning via robust adaptation. Proceedings of the 41st International Conference on Machine Learning. ICML: International Conference on Machine Learning vol. 235, 38187–38206.","apa":"Nikdan, M., Tabesh, S., Crncevic, E., &#38; Alistarh, D.-A. (2024). RoSA: Accurate parameter-efficient fine-tuning via robust adaptation. In <i>Proceedings of the 41st International Conference on Machine Learning</i> (Vol. 235, pp. 38187–38206). Vienna, Austria: ML Research Press."},"publication":"Proceedings of the 41st International Conference on Machine Learning","oa_version":"Preprint","date_published":"2024-09-01T00:00:00Z","intvolume":"       235","abstract":[{"lang":"eng","text":"We investigate parameter-efficient fine-tuning (PEFT) methods that can provide good accuracy under limited computational and memory budgets in the context of large language models (LLMs). We present a new PEFT method called Robust Adaptation (RoSA) inspired by robust principal component analysis that jointly trains low-rank\r\n and highly-sparse components on top of a set of fixed pretrained weights to efficiently approximate the performance of a full-fine-tuning (FFT) solution. Across a series of challenging generative tasks such as grade-school math and SQL query generation, which require fine-tuning for good performance, we show that RoSA outperforms LoRA, pure sparse fine-tuning, and alternative hybrid methods at the same parameter budget, and can even recover the performance of FFT on some tasks. We provide system support for RoSA to complement the training algorithm, specifically in the form of sparse GPU kernels which enable memory- and computationally-efficient training, and show that it is also compatible with low-precision base weights, resulting in the first joint representation combining quantization, low-rank and sparse approximations. Our code is available at https://github.com/IST-DASLab/RoSA."}],"publication_status":"published","author":[{"first_name":"Mahdi","id":"66374281-f394-11eb-9cf6-869147deecc0","full_name":"Nikdan, Mahdi","last_name":"Nikdan"},{"full_name":"Tabesh, Soroush","id":"06000900-6068-11ef-8d61-c2472ef2e752","last_name":"Tabesh","orcid":"0009-0003-4119-6281","first_name":"Soroush"},{"first_name":"Elvir","id":"41888001-440d-11ef-8299-d0e838b8185e","full_name":"Crncevic, Elvir","last_name":"Crncevic"},{"orcid":"0000-0003-3650-940X","first_name":"Dan-Adrian","full_name":"Alistarh, Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","last_name":"Alistarh"}],"researchdata_availability":"yes","conference":{"location":"Vienna, Austria","name":"ICML: International Conference on Machine Learning","start_date":"2024-07-21","end_date":"2024-07-27"},"quality_controlled":"1"},{"tmp":{"name":"Creative Commons Attribution 3.0 Unported (CC BY 3.0)","image":"/images/cc_by.png","short":"CC BY (3.0)","legal_code_url":"https://creativecommons.org/licenses/by/3.0/legalcode"},"date_updated":"2026-10-01T10:09:41Z","das_tickbox":"1","title":"Learning dynamical models of single and collective cell migration: a review","oa":1,"day":"04","article_type":"review","acknowledgement":"This work was supported by the Deutsche Forschungsgemeinschaft (German Research Foundation)—Project-ID 201269156—SFB 1032 (Project B12). D B B was supported by an NOMIS Fellowship and an EMBO Fellowship (ALTF 343-2022). We thank Joachim Rädler, Alexandra Fink, Erwin Frey, Pierre Ronceray, Ricard Alert, Edouard Hannezo, Henrik Flyvbjerg, Ulrich Schwarz, Joshua Shaevitz, Greg Stephens, Andrea Cavagna, Grzegorz Gradziuk, Fridtjof Brauns, Nikolas Claussen, Tom Brandstätter, Johannes Flommersfeld, Christoph Schreiber, Nicolas Arlt, Matthew Schmitt, Joris Messelink, Federico Gnesotto, Federica Mura, Bram Hoogland, Manon Wigbers, Isabella Graf, Jessica Lober, and many others for inspiring discussions. We also thank Claudia Flandoli for the artwork in figures 1, 5, 8 and 9.","volume":87,"pmid":1,"license":"https://creativecommons.org/licenses/by/3.0/","date_created":"2024-04-14T22:01:01Z","type":"journal_article","month":"04","supplementarymaterial":"no","ddc":["530"],"file":[{"creator":"dernst","file_name":"2024_ReportPhysics_Brueckner.pdf","access_level":"open_access","date_created":"2024-08-20T11:00:03Z","success":1,"date_updated":"2024-08-20T11:00:03Z","checksum":"c5910078230ade20f4dd83592e862a72","file_size":4376898,"file_id":"17451","relation":"main_file","content_type":"application/pdf"}],"dataavailabilitystatement":"No new data were created or analysed in this study.","language":[{"iso":"eng"}],"arxiv":1,"department":[{"_id":"EdHa"}],"has_accepted_license":"1","scopus_import":"1","file_date_updated":"2024-08-20T11:00:03Z","corr_author":"1","publication_identifier":{"issn":["0034-4885"],"eissn":["1361-6633"]},"publisher":"IOP Publishing","year":"2024","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","status":"public","_id":"15315","external_id":{"arxiv":["2309.00545"],"isi":["001196692400001"],"pmid":["38518358"]},"article_processing_charge":"Yes (in subscription journal)","citation":{"mla":"Brückner, David, and Chase P. Broedersz. “Learning Dynamical Models of Single and Collective Cell Migration: A Review.” <i>Reports on Progress in Physics</i>, vol. 87, no. 5, 056601, IOP Publishing, 2024, doi:<a href=\"https://doi.org/10.1088/1361-6633/ad36d2\">10.1088/1361-6633/ad36d2</a>.","chicago":"Brückner, David, and Chase P. Broedersz. “Learning Dynamical Models of Single and Collective Cell Migration: A Review.” <i>Reports on Progress in Physics</i>. IOP Publishing, 2024. <a href=\"https://doi.org/10.1088/1361-6633/ad36d2\">https://doi.org/10.1088/1361-6633/ad36d2</a>.","short":"D. Brückner, C.P. Broedersz, Reports on Progress in Physics 87 (2024).","ista":"Brückner D, Broedersz CP. 2024. Learning dynamical models of single and collective cell migration: a review. Reports on Progress in Physics. 87(5), 056601.","ieee":"D. Brückner and C. P. Broedersz, “Learning dynamical models of single and collective cell migration: a review,” <i>Reports on Progress in Physics</i>, vol. 87, no. 5. IOP Publishing, 2024.","apa":"Brückner, D., &#38; Broedersz, C. P. (2024). Learning dynamical models of single and collective cell migration: a review. <i>Reports on Progress in Physics</i>. IOP Publishing. <a href=\"https://doi.org/10.1088/1361-6633/ad36d2\">https://doi.org/10.1088/1361-6633/ad36d2</a>","ama":"Brückner D, Broedersz CP. Learning dynamical models of single and collective cell migration: a review. <i>Reports on Progress in Physics</i>. 2024;87(5). doi:<a href=\"https://doi.org/10.1088/1361-6633/ad36d2\">10.1088/1361-6633/ad36d2</a>"},"article_number":"056601","publication":"Reports on Progress in Physics","fulldoi":"https://doi.org/10.1088/1361-6633/ad36d2","project":[{"grant_number":"ALTF 343-2022","name":"A mechano-chemical theory for stem cell fate decisions in organoid development","_id":"34e2a5b5-11ca-11ed-8bc3-b2265616ef0b"}],"oa_version":"Published Version","date_published":"2024-04-04T00:00:00Z","isi":1,"abstract":[{"lang":"eng","text":"Single and collective cell migration are fundamental processes critical for physiological phenomena ranging from embryonic development and immune response to wound healing and cancer metastasis. To understand cell migration from a physical perspective, a broad variety of models for the underlying physical mechanisms that govern cell motility have been developed. A key challenge in the development of such models is how to connect them to experimental observations, which often exhibit complex stochastic behaviours. In this review, we discuss recent advances in data-driven theoretical approaches that directly connect with experimental data to infer dynamical models of stochastic cell migration. Leveraging advances in nanofabrication, image analysis, and tracking technology, experimental studies now provide unprecedented large datasets on cellular dynamics. In parallel, theoretical efforts have been directed towards integrating such datasets into physical models from the single cell to the tissue scale with the aim of conceptualising the emergent behaviour of cells. We first review how this inference problem has been addressed in both freely migrating and confined cells. Next, we discuss why these dynamics typically take the form of underdamped stochastic equations of motion, and how such equations can be inferred from data. We then review applications of data-driven inference and machine learning approaches to heterogeneity in cell behaviour, subcellular degrees of freedom, and to the collective dynamics of multicellular systems. Across these applications, we emphasise how data-driven methods can be integrated with physical active matter models of migrating cells, and help reveal how underlying molecular mechanisms control cell behaviour. Together, these data-driven approaches are a promising avenue for building physical models of cell migration directly from experimental data, and for providing conceptual links between different length-scales of description."}],"intvolume":"        87","issue":"5","publication_status":"published","author":[{"orcid":"0000-0001-7205-2975","first_name":"David","full_name":"Brückner, David","id":"e1e86031-6537-11eb-953a-f7ab92be508d","last_name":"Brückner"},{"first_name":"Chase P.","full_name":"Broedersz, Chase P.","last_name":"Broedersz"}],"researchdata_availability":"not applicable","doi":"10.1088/1361-6633/ad36d2","quality_controlled":"1"},{"has_accepted_license":"1","corr_author":"1","acknowledged_ssus":[{"_id":"Bio"}],"file_date_updated":"2024-04-02T08:54:28Z","scopus_import":"1","publication_identifier":{"eissn":["1091-6490"]},"publisher":"National Academy of Sciences","date_created":"2024-03-31T22:01:12Z","pmid":1,"acknowledgement":"We thank the Metabolomics Facility at Vienna BioCenter Core Facilities, which is a member of the Vienna BioCenter and funded by the City of Vienna through the Vienna Business Agency (shared research facility), for the LC–MS/MS analysis; and the BioImaging Facility at IST Austria for technical support and assistance. The authors want to thank N. Kastner for help with the live  cell  imaging  and  A.  Korošec  for  help  with  flow  cytometry.  This  work  was  supported by the Austrian Science Fund (FWF), grant P 36621- B (to M.R.), grant P 36667 (to W.S.), and core funding from IST Austria (to D.S.).","volume":121,"article_type":"original","supplementarymaterial":"yes","ddc":["570"],"type":"journal_article","month":"03","file":[{"content_type":"application/pdf","relation":"main_file","file_id":"15256","file_size":2483787,"checksum":"06f9e60b1146a685d58bf33999422fa8","date_updated":"2024-04-02T08:54:28Z","success":1,"access_level":"open_access","date_created":"2024-04-02T08:54:28Z","file_name":"2024_PNAS_Boytsov.pdf","creator":"dernst"}],"dataavailabilitystatement":"All study data are included in the article and/or SI Appendix.","department":[{"_id":"DaSi"}],"language":[{"iso":"eng"}],"oa":1,"day":"26","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"},"date_updated":"2026-10-01T09:36:29Z","das_tickbox":"1","title":"Orphan lysosomal solute carrier MFSD1 facilitates highly selective dipeptide transport","researchdata_availability":"yes (supplementary data)","quality_controlled":"1","doi":"10.1073/pnas.2319686121","isi":1,"fulldoi":"https://doi.org/10.1073/pnas.2319686121","date_published":"2024-03-26T00:00:00Z","oa_version":"Published Version","abstract":[{"lang":"eng","text":"Orphan solute carrier (SLC) represents a group of membrane transporters whose exact functions and substrate specificities are not known. Elucidating the function and regulation of orphan SLC transporters is not only crucial for advancing our knowledge of cellular and molecular biology but can potentially lead to the development of new therapeutic strategies. Here, we provide evidence for the biological function of a ubiquitous orphan lysosomal SLC, the Major Facilitator Superfamily Domain-containing Protein 1 (MFSD1), which has remained phylogenetically unassigned. Targeted metabolomics revealed that dipeptides containing either lysine or arginine residues accumulate in lysosomes of cells lacking MFSD1. Whole-cell patch-clamp electrophysiological recordings of HEK293-cells expressing MFSD1 on the cell surface displayed transport affinities for positively charged dipeptides in the lower mM range, while dipeptides that carry a negative net charge were not transported. This was also true for single amino acids and tripeptides, which MFSD1 failed to transport. Our results identify MFSD1 as a highly selective lysosomal lysine/arginine/histidine-containing dipeptide exporter, which functions as a uniporter."}],"intvolume":"       121","issue":"13","author":[{"first_name":"Danila","full_name":"Boytsov, Danila","last_name":"Boytsov"},{"first_name":"Gregor M.","full_name":"Madej, Gregor M.","last_name":"Madej"},{"full_name":"Horn, Georg","last_name":"Horn","first_name":"Georg"},{"first_name":"Nadine","last_name":"Blaha","full_name":"Blaha, Nadine"},{"last_name":"Köcher","full_name":"Köcher, Thomas","first_name":"Thomas"},{"first_name":"Harald H.","last_name":"Sitte","full_name":"Sitte, Harald H."},{"orcid":"0000-0001-8323-8353","first_name":"Daria E","full_name":"Siekhaus, Daria E","id":"3D224B9E-F248-11E8-B48F-1D18A9856A87","last_name":"Siekhaus"},{"full_name":"Ziegler, Christine","last_name":"Ziegler","first_name":"Christine"},{"first_name":"Walter","full_name":"Sandtner, Walter","last_name":"Sandtner"},{"orcid":"0000-0001-9588-1389","first_name":"Marko","full_name":"Roblek, Marko","id":"3047D808-F248-11E8-B48F-1D18A9856A87","last_name":"Roblek"}],"publication_status":"published","article_processing_charge":"Yes (in subscription journal)","external_id":{"isi":["001206419000003"],"pmid":["38507452"]},"citation":{"ama":"Boytsov D, Madej GM, Horn G, et al. Orphan lysosomal solute carrier MFSD1 facilitates highly selective dipeptide transport. <i>Proceedings of the National Academy of Sciences of the United States of America</i>. 2024;121(13). doi:<a href=\"https://doi.org/10.1073/pnas.2319686121\">10.1073/pnas.2319686121</a>","chicago":"Boytsov, Danila, Gregor M. Madej, Georg Horn, Nadine Blaha, Thomas Köcher, Harald H. Sitte, Daria E Siekhaus, Christine Ziegler, Walter Sandtner, and Marko Roblek. “Orphan Lysosomal Solute Carrier MFSD1 Facilitates Highly Selective Dipeptide Transport.” <i>Proceedings of the National Academy of Sciences of the United States of America</i>. National Academy of Sciences, 2024. <a href=\"https://doi.org/10.1073/pnas.2319686121\">https://doi.org/10.1073/pnas.2319686121</a>.","mla":"Boytsov, Danila, et al. “Orphan Lysosomal Solute Carrier MFSD1 Facilitates Highly Selective Dipeptide Transport.” <i>Proceedings of the National Academy of Sciences of the United States of America</i>, vol. 121, no. 13, e2319686121, National Academy of Sciences, 2024, doi:<a href=\"https://doi.org/10.1073/pnas.2319686121\">10.1073/pnas.2319686121</a>.","short":"D. Boytsov, G.M. Madej, G. Horn, N. Blaha, T. Köcher, H.H. Sitte, D.E. Siekhaus, C. Ziegler, W. Sandtner, M. Roblek, Proceedings of the National Academy of Sciences of the United States of America 121 (2024).","ieee":"D. Boytsov <i>et al.</i>, “Orphan lysosomal solute carrier MFSD1 facilitates highly selective dipeptide transport,” <i>Proceedings of the National Academy of Sciences of the United States of America</i>, vol. 121, no. 13. National Academy of Sciences, 2024.","apa":"Boytsov, D., Madej, G. M., Horn, G., Blaha, N., Köcher, T., Sitte, H. H., … Roblek, M. (2024). Orphan lysosomal solute carrier MFSD1 facilitates highly selective dipeptide transport. <i>Proceedings of the National Academy of Sciences of the United States of America</i>. National Academy of Sciences. <a href=\"https://doi.org/10.1073/pnas.2319686121\">https://doi.org/10.1073/pnas.2319686121</a>","ista":"Boytsov D, Madej GM, Horn G, Blaha N, Köcher T, Sitte HH, Siekhaus DE, Ziegler C, Sandtner W, Roblek M. 2024. Orphan lysosomal solute carrier MFSD1 facilitates highly selective dipeptide transport. Proceedings of the National Academy of Sciences of the United States of America. 121(13), e2319686121."},"article_number":"e2319686121","publication":"Proceedings of the National Academy of Sciences of the United States of America","year":"2024","_id":"15250","status":"public","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345"},{"article_number":"064503","publication":"Journal of Chemical Physics","article_processing_charge":"Yes (in subscription journal)","external_id":{"isi":["001161104900003"],"pmid":["38349632"],"arxiv":["2311.11784"]},"citation":{"ieee":"P. Robin, “Correlation-induced viscous dissipation in concentrated electrolytes,” <i>Journal of Chemical Physics</i>, vol. 160, no. 6. AIP Publishing, 2024.","ista":"Robin P. 2024. Correlation-induced viscous dissipation in concentrated electrolytes. Journal of Chemical Physics. 160(6), 064503.","apa":"Robin, P. (2024). Correlation-induced viscous dissipation in concentrated electrolytes. <i>Journal of Chemical Physics</i>. AIP Publishing. <a href=\"https://doi.org/10.1063/5.0188215\">https://doi.org/10.1063/5.0188215</a>","short":"P. Robin, Journal of Chemical Physics 160 (2024).","mla":"Robin, Paul. “Correlation-Induced Viscous Dissipation in Concentrated Electrolytes.” <i>Journal of Chemical Physics</i>, vol. 160, no. 6, 064503, AIP Publishing, 2024, doi:<a href=\"https://doi.org/10.1063/5.0188215\">10.1063/5.0188215</a>.","chicago":"Robin, Paul. “Correlation-Induced Viscous Dissipation in Concentrated Electrolytes.” <i>Journal of Chemical Physics</i>. AIP Publishing, 2024. <a href=\"https://doi.org/10.1063/5.0188215\">https://doi.org/10.1063/5.0188215</a>.","ama":"Robin P. Correlation-induced viscous dissipation in concentrated electrolytes. <i>Journal of Chemical Physics</i>. 2024;160(6). doi:<a href=\"https://doi.org/10.1063/5.0188215\">10.1063/5.0188215</a>"},"_id":"15024","status":"public","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","year":"2024","quality_controlled":"1","doi":"10.1063/5.0188215","researchdata_availability":"not applicable","intvolume":"       160","abstract":[{"lang":"eng","text":"Electrostatic correlations between ions dissolved in water are known to impact their transport properties in numerous ways, from conductivity to ion selectivity. The effects of these correlations on the solvent itself remain, however, much less clear. In particular, the addition of salt has been consistently reported to affect the solution’s viscosity, but most modeling attempts fail to reproduce experimental data even at moderate salt concentrations. Here, we use an approach based on stochastic density functional theory, which accurately captures charge fluctuations and correlations. We derive a simple analytical expression for the viscosity correction in concentrated electrolytes, by directly linking it to the liquid’s structure factor. Our prediction compares quantitatively to experimental data at all temperatures and all salt concentrations up to the saturation limit. This universal link between the microscopic structure and viscosity allows us to shed light on the nanoscale dynamics of water and ions under highly concentrated and correlated conditions."}],"issue":"6","author":[{"last_name":"Robin","id":"48c58128-57b0-11ee-9095-dc28fd97fc1d","full_name":"Robin, Paul","first_name":"Paul","orcid":"0000-0002-5728-9189"}],"publication_status":"published","fulldoi":"https://doi.org/10.1063/5.0188215","project":[{"grant_number":"101034413","name":"IST-BRIDGE: International postdoctoral program","call_identifier":"H2020","_id":"fc2ed2f7-9c52-11eb-aca3-c01059dda49c"}],"oa_version":"Published Version","date_published":"2024-02-14T00:00:00Z","isi":1,"day":"14","oa":1,"das_tickbox":"1","title":"Correlation-induced viscous dissipation in concentrated electrolytes","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"},"date_updated":"2026-10-01T10:08:50Z","ec_funded":1,"publication_identifier":{"eissn":["1089-7690"],"issn":["0021-9606"]},"publisher":"AIP Publishing","has_accepted_license":"1","corr_author":"1","scopus_import":"1","file_date_updated":"2024-02-27T08:12:52Z","dataavailabilitystatement":"Data sharing is not applicable to this article as no new data were created. Data supporting the findings of this study are accessible in the literature, as indicated throughout the article.","file":[{"checksum":"0a5e0ae70849bce674466fc054390ec0","file_size":5452738,"file_id":"15034","relation":"main_file","content_type":"application/pdf","creator":"dernst","file_name":"2024_JourChemicalPhysics_Robin.pdf","date_created":"2024-02-27T08:12:52Z","access_level":"open_access","success":1,"date_updated":"2024-02-27T08:12:52Z"}],"department":[{"_id":"EdHa"}],"arxiv":1,"language":[{"iso":"eng"}],"date_created":"2024-02-25T23:00:55Z","pmid":1,"article_type":"original","volume":160,"acknowledgement":"The author thanks Lydéric Bocquet, Baptiste Coquinot, and Mathieu Lizée for fruitful discussions. This project received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Skłodowska-Curie Grant Agreement No. 101034413.","type":"journal_article","month":"02","supplementarymaterial":"no","ddc":["540"]},{"day":"01","oa":1,"title":"Field theory of enzyme-substrate systems with restricted long-range interactions","das_tickbox":"0","date_updated":"2026-10-01T10:06:45Z","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":"American Physical Society","ec_funded":1,"publication_identifier":{"eissn":["2470-0053"],"issn":["2470-0045"]},"corr_author":"1","scopus_import":"1","file_date_updated":"2024-09-11T05:59:36Z","has_accepted_license":"1","department":[{"_id":"EdHa"}],"language":[{"iso":"eng"}],"file":[{"relation":"main_file","content_type":"application/pdf","checksum":"67fc2cc8eee3155e5c3b7380307d8284","file_size":445696,"file_id":"18053","date_created":"2024-09-11T05:59:36Z","access_level":"open_access","date_updated":"2024-09-11T05:59:36Z","success":1,"creator":"dernst","file_name":"2024_PhysReviewE_Olmeda.pdf"}],"ddc":["530"],"type":"journal_article","month":"08","supplementarymaterial":"no","pmid":1,"date_created":"2024-09-08T22:01:12Z","article_type":"original","volume":110,"acknowledgement":"We thank F. Piazza, M. Henkel, and F. Jülicher for helpful feedback and the entire Rulands group for fruitful discussions. We thank W. Reik, S. Clark, T. Lohoff, and I. Kafetzopoulos for fruitful discussions about the biological aspects of this work. This project has received funding from the European Research Council (ERC) under the European Union's Horizon 2020 research and innovation program (Grant No. 950349). This project has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie Grant No. 101034413.","publication":"Physical Review E","article_number":"024404","citation":{"ama":"Olmeda F, Rulands S. Field theory of enzyme-substrate systems with restricted long-range interactions. <i>Physical Review E</i>. 2024;110(2). doi:<a href=\"https://doi.org/10.1103/PhysRevE.110.024404\">10.1103/PhysRevE.110.024404</a>","ista":"Olmeda F, Rulands S. 2024. Field theory of enzyme-substrate systems with restricted long-range interactions. Physical Review E. 110(2), 024404.","apa":"Olmeda, F., &#38; Rulands, S. (2024). Field theory of enzyme-substrate systems with restricted long-range interactions. <i>Physical Review E</i>. American Physical Society. <a href=\"https://doi.org/10.1103/PhysRevE.110.024404\">https://doi.org/10.1103/PhysRevE.110.024404</a>","ieee":"F. Olmeda and S. Rulands, “Field theory of enzyme-substrate systems with restricted long-range interactions,” <i>Physical Review E</i>, vol. 110, no. 2. American Physical Society, 2024.","short":"F. Olmeda, S. Rulands, Physical Review E 110 (2024).","mla":"Olmeda, Fabrizio, and Steffen Rulands. “Field Theory of Enzyme-Substrate Systems with Restricted Long-Range Interactions.” <i>Physical Review E</i>, vol. 110, no. 2, 024404, American Physical Society, 2024, doi:<a href=\"https://doi.org/10.1103/PhysRevE.110.024404\">10.1103/PhysRevE.110.024404</a>.","chicago":"Olmeda, Fabrizio, and Steffen Rulands. “Field Theory of Enzyme-Substrate Systems with Restricted Long-Range Interactions.” <i>Physical Review E</i>. American Physical Society, 2024. <a href=\"https://doi.org/10.1103/PhysRevE.110.024404\">https://doi.org/10.1103/PhysRevE.110.024404</a>."},"article_processing_charge":"Yes (in subscription journal)","external_id":{"pmid":["39294986"],"isi":["001299670100004"]},"_id":"17892","status":"public","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","year":"2024","quality_controlled":"1","doi":"10.1103/PhysRevE.110.024404","researchdata_availability":"no","issue":"2","author":[{"id":"69dbf5fb-8a76-11ed-866b-fb486d8b5689","full_name":"Olmeda, Fabrizio","last_name":"Olmeda","first_name":"Fabrizio"},{"first_name":"Steffen","full_name":"Rulands, Steffen","last_name":"Rulands"}],"publication_status":"published","abstract":[{"lang":"eng","text":"Enzyme-substrate kinetics form the basis of many biomolecular processes. The interplay between substrate binding and substrate geometry can give rise to long-range interactions between enzyme binding events. Here we study a general model of enzyme-substrate kinetics with restricted long-range interactions described by an exponent −𝛾. We employ a coherent-state path integral and renormalization group approach to calculate the first moment and two-point correlation function of the enzyme-binding profile. We show that starting from an empty substrate the average occupancy follows a power law with an exponent 1/(1−𝛾) over time. The correlation function decays algebraically with two distinct spatial regimes characterized by exponents −𝛾 on short distances and −(2/3)⁢(2−𝛾) on long distances. The crossover between both regimes scales inversely with the average substrate occupancy. Our work allows associating experimental measurements of bound enzyme locations with their binding kinetics and the spatial conformation of the substrate."}],"intvolume":"       110","isi":1,"fulldoi":"https://doi.org/10.1103/PhysRevE.110.024404","project":[{"grant_number":"101034413","name":"IST-BRIDGE: International postdoctoral program","_id":"fc2ed2f7-9c52-11eb-aca3-c01059dda49c","call_identifier":"H2020"}],"date_published":"2024-08-01T00:00:00Z","oa_version":"Published Version"}]