Spurious local minima are common in two-layer relu neural networks I Safran, O Shamir International conference on machine learning, 4433-4441, 2018 | 293 | 2018 |
Depth-width tradeoffs in approximating natural functions with neural networks I Safran, O Shamir International conference on machine learning, 2979-2987, 2017 | 227* | 2017 |
On the quality of the initial basin in overspecified neural networks I Safran, O Shamir International Conference on Machine Learning, 774-782, 2016 | 143 | 2016 |
A simple explanation for the existence of adversarial examples with small hamming distance A Shamir, I Safran, E Ronen, O Dunkelman arXiv preprint arXiv:1901.10861, 2019 | 92 | 2019 |
How good is SGD with random shuffling? I Safran, O Shamir Conference on Learning Theory, 3250-3284, 2020 | 77 | 2020 |
The effects of mild over-parameterization on the optimization landscape of shallow relu neural networks IM Safran, G Yehudai, O Shamir Conference on Learning Theory, 3889-3934, 2021 | 41 | 2021 |
Depth separations in neural networks: what is actually being separated? I Safran, R Eldan, O Shamir Conference on Learning Theory, 2664-2666, 2019 | 40 | 2019 |
On the effective number of linear regions in shallow univariate relu networks: Convergence guarantees and implicit bias I Safran, G Vardi, JD Lee Advances in Neural Information Processing Systems 35, 32667-32679, 2022 | 26 | 2022 |
Random shuffling beats sgd only after many epochs on ill-conditioned problems I Safran, O Shamir Advances in Neural Information Processing Systems 34, 15151-15161, 2021 | 20 | 2021 |
Optimization-based separations for neural networks I Safran, J Lee Conference on Learning Theory, 3-64, 2022 | 15 | 2022 |
How Many Neurons Does it Take to Approximate the Maximum? I Safran, D Reichman, P Valiant Proceedings of the 2024 Annual ACM-SIAM Symposium on Discrete Algorithms …, 2024 | 2 | 2024 |
Depth Separations in Neural Networks: Separating the Dimension from the Accuracy I Safran, D Reichman, P Valiant arXiv preprint arXiv:2402.07248, 2024 | | 2024 |
Towards Theoretical Foundations for Artificial Neural Networks I Safran Weizmann Institute of Science, 2020 | | 2020 |