EPFL @ ICML 2024

ICML 2024

Below is a list of ICML 2024 papers with at least one EPFL author:

1. Imitation Learning in Discounted Linear MDPs without exploration assumptions by Luca Viano, Stratis Skoulakis and Volkan Cevher

2. Revisiting character-level adversarial attacks by Elias Abad Rocamora, Yongtao Wu, Fanghui Liu, Grigorios Chrysos and Volkan Cevher

3. Going beyond compositional generalization, DDPM can produce zero-shot interpolation by Justin Deschenaux, Igor Krawczuk, Grigorios Chrysos and Volkan Cevher

4. High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization by Yihang Chen, Fanghui Liu, Taiji Suzuki and Volkan Cevher

5. REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates by Arshia Afzal, Grigorios Chrysos, Volkan Cevher, Mahsa Shoaran

6. Truly No-Regret Learning in Constrained MDPs by Adrian Müller, Pragnya Alatur, Volkan Cevher, Giorgia Ramponi, Niao He

7. Improving SAM Requires Rethinking its Optimization Formulation by Wanyun Xie, Fabian Latorre, Kimon Antonakopoulos, Thomas Pethick, Volkan Cevher

8. Universal Gradient Methods for Stochastic Convex Optimization by Anton Rodomanov, Ali Kavis, Yongtao Wu, Kimon Antonakopoulos, Volkan Cevher

9. MADA: Meta-Adaptive Optimizers through hyper-gradient Descent by Kaan Ozkara, Can Karakus, Parameswaran Raman, Mingyi Hong, Shoham Sabach, Branislav Kveton, Volkan Cevher

10. Learning to Remove Cuts in Integer Linear Programming by Pol Puigdemont, Stratis Skoulakis, Grigorios Chrysos, Volkan Cevher

11. Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping by Ben Lonnqvist, Zhengqing Wu, Michael Herzog

12. Expand-and-Cluster: Parameter Recovery of Neural Networks by Flavio Martinelli, Berfin Simsek, Wulfram Gerstner, Johanni Brea

13. The Fundamental Limits of Least-Privilege Learning by Theresa Stadler, Bogdan Kulynych, Michael Gastpar, Nicolas Papernot, Carmela Troncoso

14. The Privacy Power of Correlated Noise in Decentralized Learning by Youssef Allouah, Anastasia Koloskova, Aymane El Firdoussi, Martin Jaggi, Rachid Guerraoui

15. LASER: Linear Compression in Wireless Distributed Optimization by Ashok Vardhan Makkuva, Marco Bondaschi, Thijs Vogels, Martin Jaggi, Hyeji Kim, Michael Gastpar

16. On Convergence of Incremental Gradient for Non-convex Smooth Functions by Anastasia Koloskova, Nikita Doikov, Sebastian U Stich, Martin Jaggi

17. Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions by Nikita Doikov, Sebastian U Stich, Martin Jaggi

18. DOGE: Domain Reweighting with Generalization Estimation by Simin Fan, Matteo Pagliardini, Martin Jaggi

19. Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks by Atli Kosson, Bettina Messmer, Martin Jaggi

20. Enabling Uncertainty Estimation in Iterative Neural Networks by Nikita Durasov, Doruk Oner, Hieu Le, Jonathan Donier, Pascal Fua

21. Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues by Antonio Orvieto, Soham De, Caglar Gulcehre, Razvan Pascanu, Samuel L Smith

22. Orchestrating Hierarchical Planning via D-Conductor and Q-Performer by Chang Chen, Fei Deng, Junyeob Baek, Kenji Kawaguchi, Caglar Gulcehre, Sungjin Ahn

23. Tackling Byzantine Clients in Federated Learning by Youssef Allouah, Sadegh Farhadkhani, Rachid Guerraoui, Nirupam Gupta, Rafael Pinot, Geovani Rizk, Sasha Voitovych

24. Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning by Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion

25. How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model by Umberto Maria Tomasini, Matthieu Wyart

26. Let Go of Your Labels with Unsupervised Transfer by Artyom Gadetsky, Yulun Jiang, Maria Brbić

27. Fine-grained Classes and How to Find Them by Matej Grcic, Artyom Gadetsky, Maria Brbić

28. Cross-domain Open-world Discovery by Shuo Wen, Maria Brbić

29. Non-linear Triple Changes Estimator for Targeted Policies by Sina Akbari, Negar Kiyavash

30. On the sample complexity of conditional independence testing with Von Mises estimator with application to causal discovery by Fateme Jamshidi, Luca Ganassali, Negar Kiyavash

31. Causal Effect Identification in LiNGAM Models with Latent Confounders by Daniele Tramontano, Saber Salehkaleybar, Yaroslav Kivva, Negar Kiyavash, Mathias Drton

32. Arrows of Time for Large Language Models by Vassilis Papadopoulos, Jérémy Wenger, Clément Hongler

33. TIC-TAC: A Framework For Improved Covariance Estimation In Deep Heteroscedastic Regression by Megh Shukla, Mathieu Salzmann, Alexandre Alahi

34. Asymptotics of feature learning in two-layer neural networks after one gradient-step by Hugo Cui, Luca Pesce, Yatin Dandi, Florent Krzakala, Yue M Lu, Lenka Zdeborová, Bruno Loureiro

35. Asymptotics of learning with deep structured (random) features by Dominik Schröder, Daniil Dmitriev, Hugo Cui, Bruno Loureiro

36. Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features by Rodrigo Veiga, Anastasia Remizova, Nicolas Macris

37. Pi-DUAL: Using privileged information to distinguish clean from noisy labels by Ke Wang, Guillermo Ortiz-Jimenez, Rodolphe Jenatton, Mark Collier, Efi Kokiopoulou, Pascal Frossard

38. Localizing Task Information for Improved Model Merging and Compression by Ke Wang*, Nikolaos Dimitriadis*, Guillermo Ortiz-Jimenez, François Fleuret, Pascal Frossard

39. Privacy Attacks in Decentralized Learning by Abdellah El Mrini, Edwige Cyffers, Aurelien Bellet

40.The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents by Yatin Dandi, Emanuele Troiani, Luca Arnaboldi, Luca Pesce, Lenka Zdeborova, Florent Krzakala

41. Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs by Luca Arnaboldi, Yatin Dandi, Florent Krzakala, Bruno Loureiro, Luca Pesce, Ludovic Stephan

42. Spectral Phase Transition and Optimal PCA in Block-Structured Spiked Models by Pierre Mergny, Justin Ko, Florent Krzakala