Ohad Shamir
Weizmann Institute of Science
H-index: 58
Asia-Israel
Top articles of Ohad Shamir
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
Depth Separation in Norm-Bounded Infinite-Width Neural Networks | arXiv preprint arXiv:2402.08808 | Suzanna Parkinson Greg Ongie Rebecca Willett Ohad Shamir Nathan Srebro | 2024/2/13 |
Accelerated zeroth-order method for non-smooth stochastic convex optimization problem with infinite variance | Advances in Neural Information Processing Systems | Nikita Kornilov Ohad Shamir Aleksandr Lobanov Darina Dvinskikh Alexander Gasnikov | 2024/2/13 |
Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks | Advances in Neural Information Processing Systems | Roey Magen Ohad Shamir | 2024/2/13 |
From tempered to benign overfitting in relu neural networks | Advances in Neural Information Processing Systems | Guy Kornowski Gilad Yehudai Ohad Shamir | 2024/2/13 |
Generalization in kernel regression under realistic assumptions | arXiv preprint arXiv:2312.15995 | Daniel Barzilai Ohad Shamir | 2023/12/26 |
Deterministic nonsmooth nonconvex optimization | Michael Jordan Guy Kornowski Tianyi Lin Ohad Shamir Manolis Zampetakis | 2023/7/12 | |
An algorithm with optimal dimension-dependence for zero-order nonsmooth nonconvex stochastic optimization | arXiv preprint arXiv:2307.04504 | Guy Kornowski Ohad Shamir | 2023/7/10 |
Implicit regularization towards rank minimization in relu networks | Nadav Timor Gal Vardi Ohad Shamir | 2023/2/13 | |
The implicit bias of benign overfitting | Journal of Machine Learning Research | Ohad Shamir | 2023 |
Reconstructing training data from trained neural networks | Advances in Neural Information Processing Systems | Niv Haim Gal Vardi Gilad Yehudai Ohad Shamir Michal Irani | 2022/12/6 |
Depth separations in neural networks: What is actually being separated? | Constructive approximation | Itay Safran Ronen Eldan Ohad Shamir | 2022/2 |
The sample complexity of one-hidden-layer neural networks | Advances in Neural Information Processing Systems | Gal Vardi Ohad Shamir Nati Srebro | 2022/12/6 |
Oracle complexity in nonsmooth nonconvex optimization | Journal of Machine Learning Research | Guy Kornowski Ohad Shamir | 2022 |
Gradient methods provably converge to non-robust networks | Advances in Neural Information Processing Systems | Gal Vardi Gilad Yehudai Ohad Shamir | 2022/12/6 |
Elephant in the Room: Non-Smooth Non-Convex Optimization. | Ohad Shamir | 2022 | |
On margin maximization in linear and relu networks | Advances in Neural Information Processing Systems | Gal Vardi Ohad Shamir Nati Srebro | 2022/12/6 |
On the complexity of finding small subgradients in nonsmooth optimization | arXiv preprint arXiv:2209.10346 | Guy Kornowski Ohad Shamir | 2022/9/21 |
Width is less important than depth in ReLU neural networks | Gal Vardi Gilad Yehudai Ohad Shamir | 2022/6/28 | |
Gradient methods never overfit on separable data | Journal of Machine Learning Research | Ohad Shamir | 2021 |
The connection between approximation, depth separation and learnability in neural networks | Eran Malach Gilad Yehudai Shai Shalev-Schwartz Ohad Shamir | 2021/7/21 |