Gal Vardi
Weizmann Institute of Science
H-index: 14
Asia-Israel
Top articles of Gal Vardi
Deconstructing data reconstruction: Multiclass, weight decay and general losses
Advances in Neural Information Processing Systems
2024/2/13
Most Neural Networks Are Almost Learnable
Advances in Neural Information Processing Systems
2024/2/13
Amit Daniely
H-Index: 16
Gal Vardi
H-Index: 5
The double-edged sword of implicit bias: Generalization vs. robustness in relu networks
Advances in Neural Information Processing Systems
2024/2/13
Computational complexity of learning neural networks: Smoothness and degeneracy
Advances in Neural Information Processing Systems
2024/2/13
Amit Daniely
H-Index: 16
Gal Vardi
H-Index: 5
Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces
Advances in Neural Information Processing Systems
2024/2/13
Gilad Yehudai
H-Index: 3
Gal Vardi
H-Index: 5
Benign overfitting and grokking in relu networks for xor cluster data
arXiv preprint arXiv:2310.02541
2023/10/4
Noisy interpolation learning with shallow univariate relu networks
arXiv preprint arXiv:2307.15396
2023/7/28
Gal Vardi
H-Index: 5
Nathan Srebro
H-Index: 52
Benign overfitting in linear classifiers and leaky relu networks from kkt conditions for margin maximization
2023/7/12
An agnostic view on the cost of overfitting in (kernel) ridge regression
arXiv preprint arXiv:2306.13185
2023/6/22
Gal Vardi
H-Index: 5
Nathan Srebro
H-Index: 52
The magazine archive includes every article published in Communications of the ACM for over the past 50 years.
Communications of the ACM
2010/7
On the implicit bias in deep-learning algorithms
2023/5/24
Gal Vardi
H-Index: 5
Reconstructing Training Data from Multiclass Neural Networks
arXiv preprint arXiv:2305.03350
2023/5/5
Implicit regularization towards rank minimization in relu networks
2023/2/13
Gal Vardi
H-Index: 5
Ohad Shamir
H-Index: 41
Reconstructing training data from trained neural networks
Advances in Neural Information Processing Systems
2022/12/6
On the effective number of linear regions in shallow univariate relu networks: Convergence guarantees and implicit bias
Advances in Neural Information Processing Systems
2022/12/6
Itay Safran
H-Index: 6
Gal Vardi
H-Index: 5
The sample complexity of one-hidden-layer neural networks
Advances in Neural Information Processing Systems
2022/12/6
Gal Vardi
H-Index: 5
Ohad Shamir
H-Index: 41
Gradient methods provably converge to non-robust networks
Advances in Neural Information Processing Systems
2022/12/6
On margin maximization in linear and relu networks
Advances in Neural Information Processing Systems
2022/12/6
Gal Vardi
H-Index: 5
Ohad Shamir
H-Index: 41
On convexity and linear mode connectivity in neural networks
2022/11/23
Implicit bias in leaky relu networks trained on high-dimensional data
arXiv preprint arXiv:2210.07082
2022/10/13