@unpublished{14963, abstract = {Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT) pipelines. Unfortunately, they lack two key properties: objects are often split into parts and are not consistently tracked over time. In fact, state-of-the-art models achieve pixel-level accuracy and temporal consistency by relying on supervised object detection with additional ID labels for the association through time. This paper proposes a video object-centric model for MOT. It consists of an index-merge module that adapts the object-centric slots into detection outputs and an object memory module that builds complete object prototypes to handle occlusions. Benefited from object-centric learning, we only require sparse detection labels (0%-6.25%) for object localization and feature binding. Relying on our self-supervised Expectation-Maximization-inspired loss for object association, our approach requires no ID labels. Our experiments significantly narrow the gap between the existing object-centric model and the fully supervised state-of-the-art and outperform several unsupervised trackers.}, author = {Zhao, Zixu and Wang, Jiaze and Horn, Max and Ding, Yizhuo and He, Tong and Bai, Zechen and Zietlow, Dominik and Carl-Johann Simon-Gabriel, Carl-Johann Simon-Gabriel and Shuai, Bing and Tu, Zhuowen and Brox, Thomas and Schiele, Bernt and Fu, Yanwei and Locatello, Francesco and Zhang, Zheng and Xiao, Tianjun}, booktitle = {arXiv}, title = {{Object-centric multiple object tracking}}, doi = {10.48550/arXiv.2309.00233}, year = {2023}, } @misc{14965, abstract = {A method of determining a correspondence between a first biological property of a cell and one or more further biological properties of cells is provided. The first biological property and the further biological properties are determined by different analysis techniques and each are contained in a respective one of a plurality of sets of biological properties. The method includes the steps of: converting the plurality of sets of biological properties into corresponding representations in a representation format which is invariant to the technologies used to derive the biological properties; determining, in said representation format, a representation from each of the converted sets of further biological properties which most closely matches the first representation of the first biological property; and re-converting the determined representations from the representation format back to the biological properties associated with the determined representations and thereby determining a correspondence between the first biological property and each of the further biological properties.}, author = {Ficek, Joanna and Lehmann, Kjong-Van and Locatello, Francesco and Raetsch, Gunnar and Stark, Stefan}, pages = {9}, title = {{Methods of determining correspondences between biological properties of cells}}, year = {2023}, } @inproceedings{14974, abstract = {The field of machine learning and AI has witnessed remarkable breakthroughs with the emergence of LLMs, which have also sparked a lively debate in the causal community. As researchers in this field, we are interested in exploring how LLMs relate to causality research, and how we can leverage the technology to advance it. In the second conference of Causal Learning and Reasoning (CLeaR), 2023, we held a round table discussion to gather and integrate the diverse perspectives of the CLeaR community on this topic. There is a general consensus that LLMs are not yet capable of causal reasoning at the current stage but has a lot of potential with public available information by CLeaR 2023. Enhancing causal machine learning is vital not only for its own sake but also to help LLMs improve their performance, especially regarding trustworthiness. In this document, we present both the summary and the raw outcome of the round table discussion. We acknowledge that with the progress of both fields, the opportunities and impact may rapidly change. We will repeat the same exercise in CLeaR 2024 to document the evolution.}, author = {Zhang, Cheng and Janzing, Dominik and van der Schaar, Mihaela and Locatello, Francesco and Spirtes, Peter and Zhang, Kun and Schölkopf, Bernhard and Uhler, Caroline}, booktitle = {2nd Conference on Causal Learning and Reasoning}, location = {Tübingen, Germany}, title = {{Causality in the time of LLMs: Round table discussion results of CLeaR 2023}}, year = {2023}, } @article{14985, abstract = {Lead sulfide (PbS) presents large potential in thermoelectric application due to its earth-abundant S element. However, its inferior average ZT (ZTave) value makes PbS less competitive with its analogs PbTe and PbSe. To promote its thermoelectric performance, this study implements strategies of continuous Se alloying and Cu interstitial doping to synergistically tune thermal and electrical transport properties in n-type PbS. First, the lattice parameter of 5.93 Å in PbS is linearly expanded to 6.03 Å in PbS0.5Se0.5 with increasing Se alloying content. This expanded lattice in Se-alloyed PbS not only intensifies phonon scattering but also facilitates the formation of Cu interstitials. Based on the PbS0.6Se0.4 content with the minimal lattice thermal conductivity, Cu interstitials are introduced to improve the electron density, thus boosting the peak power factor, from 3.88 μW cm−1 K−2 in PbS0.6Se0.4 to 20.58 μW cm−1 K−2 in PbS0.6Se0.4−1%Cu. Meanwhile, the lattice thermal conductivity in PbS0.6Se0.4−x%Cu (x = 0–2) is further suppressed due to the strong strain field caused by Cu interstitials. Finally, with the lowered thermal conductivity and high electrical transport properties, a peak ZT ~1.1 and ZTave ~0.82 can be achieved in PbS0.6Se0.4 − 1%Cu at 300–773K, which outperforms previously reported n-type PbS.}, author = {Liu, Zhengtao and Hong, Tao and Xu, Liqing and Wang, Sining and Gao, Xiang and Chang, Cheng and Ding, Xiangdong and Xiao, Yu and Zhao, Li‐Dong}, issn = {2767-441X}, journal = {Interdisciplinary Materials}, number = {1}, pages = {161--170}, publisher = {Wiley}, title = {{Lattice expansion enables interstitial doping to achieve a high average ZT in n‐type PbS}}, doi = {10.1002/idm2.12056}, volume = {2}, year = {2023}, } @inproceedings{14989, abstract = {Encryption alone is not enough for secure end-to end encrypted messaging: a server must also honestly serve public keys to users. Key transparency has been presented as an efficient solution for detecting (and hence deterring) a server that attempts to dishonestly serve keys. Key transparency involves two major components: (1) a username to public key mapping, stored and cryptographically committed to by the server, and, (2) an outof-band consistency protocol for serving short commitments to users. In the setting of real-world deployments and supporting production scale, new challenges must be considered for both of these components. We enumerate these challenges and provide solutions to address them. In particular, we design and implement a memory-optimized and privacy-preserving verifiable data structure for committing to the username to public key store. To make this implementation viable for production, we also integrate support for persistent and distributed storage. We also propose a future-facing solution, termed “compaction”, as a mechanism for mitigating practical issues that arise from dealing with infinitely growing server data structures. Finally, we implement a consensusless solution that achieves the minimum requirements for a service that consistently distributes commitments for a transparency application, providing a much more efficient protocol for distributing small and consistent commitments to users. This culminates in our production-grade implementation of a key transparency system (Parakeet) which we have open-sourced, along with a demonstration of feasibility through our benchmarks.}, author = {Malvai, Harjasleen and Kokoris Kogias, Eleftherios and Sonnino, Alberto and Ghosh, Esha and Oztürk, Ercan and Lewi, Kevin and Lawlor, Sean}, booktitle = {Proceedings of the 2023 Network and Distributed System Security Symposium}, isbn = {1891562835}, location = {San Diego, CA, United States}, publisher = {Internet Society}, title = {{Parakeet: Practical key transparency for end-to-end eEncrypted messaging}}, doi = {10.14722/ndss.2023.24545}, year = {2023}, } @misc{14990, abstract = {The software artefact to evaluate the approximation of stationary distributions implementation.}, author = {Meggendorfer, Tobias}, publisher = {Zenodo}, title = {{Artefact for: Correct Approximation of Stationary Distributions}}, doi = {10.5281/ZENODO.7548214}, year = {2023}, } @misc{14991, abstract = {This repository contains the data, scripts, WRF codes and files required to reproduce the results of the manuscript "Assessing Memory in Convection Schemes Using Idealized Tests" submitted to the Journal of Advances in Modeling Earth Systems (JAMES).}, author = {Hwong, Yi-Ling and Colin, Maxime and Aglas, Philipp and Muller, Caroline J and Sherwood, Steven C.}, publisher = {Zenodo}, title = {{Data-assessing memory in convection schemes using idealized tests}}, doi = {10.5281/ZENODO.7757041}, year = {2023}, } @inbook{14992, abstract = {In this chapter we first review the Levy–Lieb functional, which gives the lowest kinetic and interaction energy that can be reached with all possible quantum states having a given density. We discuss two possible convex generalizations of this functional, corresponding to using mixed canonical and grand-canonical states, respectively. We present some recent works about the local density approximation, in which the functionals get replaced by purely local functionals constructed using the uniform electron gas energy per unit volume. We then review the known upper and lower bounds on the Levy–Lieb functionals. We start with the kinetic energy alone, then turn to the classical interaction alone, before we are able to put everything together. A later section is devoted to the Hohenberg–Kohn theorem and the role of many-body unique continuation in its proof.}, author = {Lewin, Mathieu and Lieb, Elliott H. and Seiringer, Robert}, booktitle = {Density Functional Theory}, editor = {Cances, Eric and Friesecke, Gero}, isbn = {9783031223396}, issn = {3005-0286}, pages = {115--182}, publisher = {Springer}, title = {{Universal Functionals in Density Functional Theory}}, doi = {10.1007/978-3-031-22340-2_3}, year = {2023}, } @inproceedings{14993, abstract = {Traditional top-down approaches for global health have historically failed to achieve social progress (Hoffman et al., 2015; Hoffman & Røttingen, 2015). Recently, however, a more holistic, multi-level approach termed One Health (OH) (Osterhaus et al., 2020) is being adopted. Several sets of challenges have been identified for the implementation of OH (dos S. Ribeiro et al., 2019), including policy and funding, education and training, and multi-actor, multi-domain, and multi-level collaborations. These exist despite the increasing accessibility to knowledge and digital collaborative research tools through the internet. To address some of these challenges, we propose a general framework for grassroots community-based means of participatory research. Additionally, we present a specific roadmap to create a Machine Learning for Global Health community in Africa. The proposed framework aims to enable any small group of individuals with scarce resources to build and sustain an online community within approximately two years. We provide a discussion on the potential impact of the proposed framework for global health research collaborations.}, author = {Currin, Christopher and Asiedu , Mercy Nyamewaa and Fourie, Chris and Rosman, Benjamin and Turki, Houcemeddine and Lambebo Tonja, Atnafu and Abbott, Jade and Ajala, Marvellous and Adedayo, Sadiq Adewale and Emezue, Chris Chinenye and Machangara, Daphne}, booktitle = {1st Workshop on Machine Learning & Global Health}, location = {Kigali, Rwanda}, publisher = {OpenReview}, title = {{A framework for grassroots research collaboration in machine learning and global health}}, year = {2023}, } @misc{14994, abstract = {This resource contains the artifacts for reproducing the experimental results presented in the paper titled "A Flexible Toolchain for Symbolic Rabin Games under Fair and Stochastic Uncertainties" that has been submitted in CAV 2023.}, author = {Majumdar, Rupak and Mallik, Kaushik and Rychlicki, Mateusz and Schmuck, Anne-Kathrin and Soudjani, Sadegh}, publisher = {Zenodo}, title = {{A flexible toolchain for symbolic rabin games under fair and stochastic uncertainties}}, doi = {10.5281/ZENODO.7877790}, year = {2023}, } @misc{14995, abstract = {Lincheck is a new practical and user-friendly framework for testing concurrent data structures on the Java Virtual Machine (JVM). It provides a simple and declarative way to write concurrent tests. Instead of describing how to perform the test, users specify what to test by declaring all the operations to examine; the framework automatically handles the rest. As a result, tests written with Lincheck are concise and easy to understand. The artifact presents a collection of Lincheck tests that discover new bugs in popular libraries and implementations from the concurrency literature -- they are listed in Table 1, Section 3. To evaluate the performance of Lincheck analysis, the collection of tests also includes those which check correct data structures and, thus, always succeed. Similarly to Table 2, Section 3, the experiments demonstrate the reasonable time to perform a test. Finally, Lincheck provides user-friendly output with an easy-to-follow trace to reproduce a detected error, significantly simplifying further investigation.}, author = {Koval, Nikita and Fedorov, Alexander and Sokolova, Maria and Tsitelov, Dmitry and Alistarh, Dan-Adrian}, publisher = {Zenodo}, title = {{Lincheck: A practical framework for testing concurrent data structures on JVM}}, doi = {10.5281/ZENODO.7877757}, year = {2023}, } @inproceedings{15023, abstract = {Reinforcement learning has shown promising results in learning neural network policies for complicated control tasks. However, the lack of formal guarantees about the behavior of such policies remains an impediment to their deployment. We propose a novel method for learning a composition of neural network policies in stochastic environments, along with a formal certificate which guarantees that a specification over the policy's behavior is satisfied with the desired probability. Unlike prior work on verifiable RL, our approach leverages the compositional nature of logical specifications provided in SpectRL, to learn over graphs of probabilistic reach-avoid specifications. The formal guarantees are provided by learning neural network policies together with reach-avoid supermartingales (RASM) for the graph’s sub-tasks and then composing them into a global policy. We also derive a tighter lower bound compared to previous work on the probability of reach-avoidance implied by a RASM, which is required to find a compositional policy with an acceptable probabilistic threshold for complex tasks with multiple edge policies. We implement a prototype of our approach and evaluate it on a Stochastic Nine Rooms environment.}, author = {Zikelic, Dorde and Lechner, Mathias and Verma, Abhinav and Chatterjee, Krishnendu and Henzinger, Thomas A}, booktitle = {37th Conference on Neural Information Processing Systems}, location = {New Orleans, LO, United States}, title = {{Compositional policy learning in stochastic control systems with formal guarantees}}, year = {2023}, } @misc{15027, abstract = {This data repository underpins the paper, published in PNAS (doi pending) and bioarxiv (doi: https://doi.org/10.1101/2023.07.05.547777).}, author = {Curk, Samo}, publisher = {Figshare}, title = {{aggregation_data}}, year = {2023}, } @misc{15035, abstract = {This artifact aims to reproduce experiments from the paper Monitoring Hyperproperties With Prefix Transducers accepted at RV'23, and give further pointers to implementation of prefix transducers. It has two parts: a pre-compiled docker image and sources that one can use to compile (locally or in docker) the software and run the experiments.}, author = {Chalupa, Marek and Henzinger, Thomas A}, publisher = {Zenodo}, title = {{Monitoring hyperproperties with prefix transducers}}, doi = {10.5281/ZENODO.8191723}, year = {2023}, } @article{15173, abstract = {We show that the number of linear spaces on a set of n points and the number of rank-3 matroids on a ground set of size n are both of the form (cn+o(n))n2/6, where c=e3√/2−3(1+3–√)/2. This is the final piece of the puzzle for enumerating fixed-rank matroids at this level of accuracy: the numbers of rank-1 and rank-2 matroids on a ground set of size n have exact representations in terms of well-known combinatorial functions, and it was recently proved by van der Hofstad, Pendavingh, and van der Pol that for constant r≥4 there are (e1−rn+o(n))nr−1/r! rank-r matroids on a ground set of size n. In our proof, we introduce a new approach for bounding the number of clique decompositions of a complete graph, using quasirandomness instead of the so-called entropy method that is common in this area.}, author = {Kwan, Matthew Alan and Sah, Ashwin and Sawhney, Mehtaab}, issn = {1778-3569}, journal = {Comptes Rendus Mathematique}, number = {G2}, pages = {565--575}, publisher = {Academie des Sciences}, title = {{Enumerating matroids and linear spaces}}, doi = {10.5802/crmath.423}, volume = {361}, year = {2023}, } @misc{15292, abstract = {We present a rigid body animation technique which prevents solids from interpenetrating, dissipates energy through friction, and propagates shocks through contacts. We employ the Alternating Direction Method of Multipliers (ADMM) to couple non-smooth Coulomb friction with impact propagation, allowing efficient and accurate non-smooth dynamics along with a correct transmission of impacts through assemblies of rigid bodies. We further extend our method to model adhesion, dynamic friction and lubricated contact.}, author = {Chen, Yi-Lu and Ly, Mickaël and Wojtan, Christopher J}, booktitle = {Proceedings of the ACM SIGGRAPH/Eurographics Symposium on Computer Animation}, location = {Los Angeles, CA, United States}, publisher = {ACM}, title = {{Unified treatment of contact, friction and shock-propagation in rigid body animation}}, doi = {10.1145/3606037.3606836}, year = {2023}, } @inproceedings{15363, abstract = {Knowledge distillation is a popular approach for enhancing the performance of "student" models, with lower representational capacity, by taking advantage of more powerful "teacher" models. Despite its apparent simplicity, the underlying mechanics behind knowledge distillation (KD) are not yet fully understood. In this work, we shed new light on the inner workings of this method, by examining it from an optimization perspective. Specifically, we show that, in the context of linear and deep linear models, KD can be interpreted as a novel type of stochastic variance reduction mechanism. We provide a detailed convergence analysis of the resulting dynamics, which hold under standard assumptions for both strongly-convex and non-convex losses, showing that KD acts as a form of \emph{partial variance reduction}, which can reduce the stochastic gradient noise, but may not eliminate it completely, depending on the properties of the teacher'' model. Our analysis puts further emphasis on the need for careful parametrization of KD, in particular w.r.t. the weighting of the distillation loss, and is validated empirically on both linear models and deep neural networks.}, author = {Safaryan, Mher and Peste, Elena-Alexandra and Alistarh, Dan-Adrian}, booktitle = {36th Conference on Neural Information Processing Systems}, issn = {1049-5258}, location = {New Orleans, LA, United States}, title = {{Knowledge distillation performs partial variance reduction}}, volume = {36}, year = {2023}, } @inproceedings{15364, abstract = {Clustering is a fundamental problem in unsupervised machine learning with many applications in data analysis. Popular clustering algorithms such as Lloyd's algorithm and k-means++ can make Ω(ndk) time when clustering n points in a d-dimensional space (represented by an n×d matrix X) into k clusters. On massive datasets with moderate to large k, the multiplicative k factor can become very expensive. We introduce a simple randomized clustering algorithm that provably runs in expected time O(nnz(X)+nlogn) for arbitrary k. Here nnz(X) is the total number of non-zero entries in the input dataset X, which is upper bounded by nd and can be significantly smaller for sparse datasets. We prove that our algorithm achieves approximation ratio ˜O(k4) on any input dataset for the k-means objective, and our experiments show that the quality of the clusters found by our algorithm is usually much better than this worst-case bound. We use our algorithm for k-means clustering and for coreset construction; our experiments show that it gives a new tradeoff between running time and cluster quality compared to previous state-of-the-art methods for these tasks. Our theoretical analysis is based on novel results of independent interest. We show that the approximation ratio achieved after a random one-dimensional projection can be lifted to the original points and that k-means++ seeding can be implemented in expected time O(nlogn) in one dimension.}, author = {Charikar, Moses and Hu, Lunjia and Henzinger, Monika H and Vötsch, Maximilian and Waingarten, Erik}, booktitle = {37th Conference on Neural Information Processing Systems}, issn = {1049-5258}, location = {New Orleans, LA, United States}, title = {{Simple, scalable and effective clustering via one-dimensional projections}}, volume = {36}, year = {2023}, } @article{10770, abstract = {Mathematical models often aim to describe a complicated mechanism in a cohesive and simple manner. However, reaching perfect balance between being simple enough or overly simplistic is a challenging task. Frequently, game-theoretic models have an underlying assumption that players, whenever they choose to execute a specific action, do so perfectly. In fact, it is rare that action execution perfectly coincides with intentions of individuals, giving rise to behavioural mistakes. The concept of incompetence of players was suggested to address this issue in game-theoretic settings. Under the assumption of incompetence, players have non-zero probabilities of executing a different strategy from the one they chose, leading to stochastic outcomes of the interactions. In this article, we survey results related to the concept of incompetence in classic as well as evolutionary game theory and provide several new results. We also suggest future extensions of the model and argue why it is important to take into account behavioural mistakes when analysing interactions among players in both economic and biological settings.}, author = {Graham, Thomas and Kleshnina, Maria and Filar, Jerzy A.}, issn = {2153-0793}, journal = {Dynamic Games and Applications}, pages = {231--264}, publisher = {Springer Nature}, title = {{Where do mistakes lead? A survey of games with incompetent players}}, doi = {10.1007/s13235-022-00425-3}, volume = {13}, year = {2023}, } @article{11434, abstract = {The Indian summer monsoon rainfall (ISMR) has been declining since the 1950s. However, since 2002 it is reported to have revived. For these observed changes in the ISMR, several explanations have been reported. Among these explanations, however, the role of the eastern equatorial Indian Ocean (EEIO) is missing despite being one of the warmest regions in the Indian Ocean, and monotonously warming. A recent study reported that EEIO warming impacts the rainfall over northern India. Here we report that warming in the EEIO weakens the low-level Indian summer monsoon circulation and reduces ISMR. A warm EEIO drives easterly winds in the Indo–Pacific sector as a Gill response. The warm EEIO also enhances nocturnal convection offshore the western coast of Sumatra. The latent heating associated with the increased convection augments the Gill response and the resultant circulation opposes the monsoon low-level circulation and weakens the seasonal rainfall.}, author = {Goswami, Bidyut B}, issn = {1432-0894}, journal = {Climate Dynamics}, pages = {427--442}, publisher = {Springer Nature}, title = {{Role of the eastern equatorial Indian Ocean warming in the Indian summer monsoon rainfall trend}}, doi = {10.1007/s00382-022-06337-7}, volume = {60}, year = {2023}, }