Samy Jelassi

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 30

Top Topics

Gradient Method

Top Venues

J. Mach. Learn. Res.

Publications

Ahmet Cagri Duzgun, Samy Jelassi, Yuanzhi Li
How Does Overparameterization Affect Features? CoRR (2024)
Kaiying Hou, David Brandfonbrener, Sham M. Kakade, Samy Jelassi, Eran Malach
Universal Length Generalization with Turing Programs. CoRR (2024)
Kenneth Li, Samy Jelassi, Hugh Zhang, Sham M. Kakade, Martin Wattenberg, David Brandfonbrener
Q-Probe: A Lightweight Approach to Reward Maximization for Language Models. CoRR (2024)
Samy Jelassi, David Brandfonbrener, Sham M. Kakade, Eran Malach
Repeat After Me: Transformers are Better than State Space Models at Copying. CoRR (2024)
Samy Jelassi, Stéphane d'Ascoli, Carles Domingo-Enrich, Yuhuai Wu, Yuanzhi Li, François Charton
Length Generalization in Arithmetic Transformers. CoRR (2023)
Samy Jelassi, Boris Hanin, Ziwei Ji, Sashank J. Reddi, Srinadh Bhojanapalli, Sanjiv Kumar
Depth Dependence of μP Learning Rates in ReLU MLPs. CoRR (2023)
Samy Jelassi, Yuanzhi Li
Towards understanding how momentum improves generalization in deep learning. CoRR (2022)
Samy Jelassi, David Dobre, Arthur Mensch, Yuanzhi Li, Gauthier Gidel
Dissecting adaptive methods in GANs. CoRR (2022)
Samy Jelassi, Michael E. Sander, Yuanzhi Li
Vision Transformers provably learn spatial structure. CoRR (2022)
Luca Venturi, Samy Jelassi, Tristan Ozuch, Joan Bruna
Depth separation beyond radial functions. J. Mach. Learn. Res. 23 (2022)
Aaron Defazio, Samy Jelassi
A Momentumized, Adaptive, Dual Averaged Gradient Method. J. Mach. Learn. Res. 23 (2022)
Samy Jelassi, Michael E. Sander, Yuanzhi Li
Vision Transformers provably learn spatial structure. NeurIPS (2022)
Samy Jelassi, Yuanzhi Li
Towards understanding how momentum improves generalization in deep learning. ICML (2022)
Luca Venturi, Samy Jelassi, Tristan Ozuch, Joan Bruna
Depth separation beyond radial functions. CoRR (2021)
Jad Rahme, Samy Jelassi, Joan Bruna, S. Matthew Weinberg
A Permutation-Equivariant Neural Network Architecture For Auction Design. AAAI (2021)
Jad Rahme, Samy Jelassi, S. Matthew Weinberg
Auction Learning as a Two-Player Game. ICLR (2021)
Aaron Defazio, Samy Jelassi
Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization. CoRR (2021)
Jad Rahme, Samy Jelassi, Joan Bruna, S. Matthew Weinberg
A Permutation-Equivariant Neural Network Architecture For Auction Design. CoRR (2020)
Carles Domingo-Enrich, Samy Jelassi, Arthur Mensch, Grant M. Rotskoff, Joan Bruna
A mean-field analysis of two-player zero-sum games. CoRR (2020)
Jad Rahme, Samy Jelassi, S. Matthew Weinberg
Auction learning as a two-player game. CoRR (2020)
Samy Jelassi, Aaron Defazio
Dual Averaging is Surprisingly Effective for Deep Learning Optimization. CoRR (2020)
Carles Domingo-Enrich, Samy Jelassi, Arthur Mensch, Grant M. Rotskoff, Joan Bruna
A mean-field analysis of two-player zero-sum games. NeurIPS (2020)
Samy Jelassi, Carles Domingo-Enrich, Damien Scieur, Arthur Mensch, Joan Bruna
Extra-gradient with player sampling for faster convergence in n-player games. ICML (2020)
Othmane Sebbouh, Nidham Gazagnadou, Samy Jelassi, Francis R. Bach, Robert M. Gower
Towards closing the gap between the theory and practice of SVRG. CoRR (2019)
Othmane Sebbouh, Nidham Gazagnadou, Samy Jelassi, Francis R. Bach, Robert M. Gower
Towards closing the gap between the theory and practice of SVRG. NeurIPS (2019)
Grant M. Rotskoff, Samy Jelassi, Joan Bruna, Eric Vanden-Eijnden
Global convergence of neuron birth-death dynamics. CoRR (2019)
Grant M. Rotskoff, Samy Jelassi, Joan Bruna, Eric Vanden-Eijnden
Neuron birth-death dynamics accelerates gradient descent and converges asymptotically. ICML (2019)
Samy Jelassi, Carles Domingo-Enrich, Damien Scieur, Arthur Mensch, Joan Bruna
Extra-gradient with player sampling for provable fast convergence in n-player games. CoRR (2019)
Thomas Pumir, Samy Jelassi, Nicolas Boumal
Smoothed analysis of the low-rank approach for smooth semidefinite programs. CoRR (2018)
Thomas Pumir, Samy Jelassi, Nicolas Boumal
Smoothed analysis of the low-rank approach for smooth semidefinite programs. NeurIPS (2018)