| Reconstructing training data from trained neural networks N Haim, G Vardi, G Yehudai, O Shamir, M Irani Advances in Neural Information Processing Systems 35, 22911-22924, 2022 | 154 | 2022 |
| On the implicit bias in deep-learning algorithms G Vardi Communications of the ACM 66 (6), 86-93, 2023 | 93 | 2023 |
| Implicit regularization in relu networks with the square loss G Vardi, O Shamir Conference on Learning Theory, 4224-4258, 2021 | 64 | 2021 |
| Implicit regularization towards rank minimization in relu networks N Timor, G Vardi, O Shamir International Conference on Algorithmic Learning Theory, 1429-1459, 2023 | 58 | 2023 |
| Implicit bias in leaky relu networks trained on high-dimensional data S Frei, G Vardi, PL Bartlett, N Srebro, W Hu arXiv preprint arXiv:2210.07082, 2022 | 53 | 2022 |
| Benign overfitting in linear classifiers and leaky relu networks from kkt conditions for margin maximization S Frei, G Vardi, P Bartlett, N Srebro The Thirty Sixth Annual Conference on Learning Theory, 3173-3228, 2023 | 38 | 2023 |
| From local pseudorandom generators to hardness of learning A Daniely, G Vardi Conference on Learning Theory, 1358-1394, 2021 | 36 | 2021 |
| 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 | 34 | 2022 |
| On margin maximization in linear and relu networks G Vardi, O Shamir, N Srebro Advances in Neural Information Processing Systems 35, 37024-37036, 2022 | 31 | 2022 |
| On the optimal memorization power of relu neural networks G Vardi, G Yehudai, O Shamir arXiv preprint arXiv:2110.03187, 2021 | 30 | 2021 |
| Gradient methods provably converge to non-robust networks G Vardi, G Yehudai, O Shamir Advances in Neural Information Processing Systems 35, 20921-20932, 2022 | 28 | 2022 |
| Benign overfitting and grokking in relu networks for xor cluster data Z Xu, Y Wang, S Frei, G Vardi, W Hu arXiv preprint arXiv:2310.02541, 2023 | 27 | 2023 |
| Size and depth separation in approximating benign functions with neural networks G Vardi, D Reichman, T Pitassi, O Shamir Conference on Learning Theory, 4195-4223, 2021 | 26* | 2021 |
| Neural networks with small weights and depth-separation barriers G Vardi, O Shamir Advances in neural information processing systems 33, 19433-19442, 2020 | 26 | 2020 |
| Learning a single neuron with bias using gradient descent G Vardi, G Yehudai, O Shamir Advances in Neural Information Processing Systems 34, 28690-28700, 2021 | 24 | 2021 |
| Hardness of learning neural networks with natural weights A Daniely, G Vardi Advances in Neural Information Processing Systems 33, 930-940, 2020 | 24 | 2020 |
| The double-edged sword of implicit bias: Generalization vs. robustness in relu networks S Frei, G Vardi, P Bartlett, N Srebro Advances in Neural Information Processing Systems 36, 2024 | 22 | 2024 |
| On convexity and linear mode connectivity in neural networks D Yunis, KK Patel, PHP Savarese, G Vardi, J Frankle, M Walter, K Livescu, ... OPT 2022: Optimization for Machine Learning (NeurIPS 2022 Workshop), 2022 | 19 | 2022 |
| Deconstructing data reconstruction: Multiclass, weight decay and general losses G Buzaglo, N Haim, G Yehudai, G Vardi, Y Oz, Y Nikankin, M Irani Advances in Neural Information Processing Systems 36, 2024 | 18 | 2024 |
| Width is less important than depth in relu neural networks G Vardi, G Yehudai, O Shamir Conference on learning theory, 1249-1281, 2022 | 17 | 2022 |
