| Toward deeper understanding of neural networks: The power of initialization and a dual view on expressivity A Daniely, R Frostig, Y Singer Advances In Neural Information Processing Systems, 2253-2261, 2016 | 83 | 2016 |
| Complexity theoretic limitations on learning DNF’s A Daniely, S Shalev-Shwartz Conference on Learning Theory, 815-830, 2016 | 65 | 2016 |
| From average case complexity to improper learning complexity A Daniely, N Linial, S Shalev-Shwartz arXiv preprint arXiv:1311.2272, 2013 | 63 | 2013 |
| Complexity theoretic limitations on learning halfspaces A Daniely Proceedings of the forty-eighth annual ACM symposium on Theory of Computing …, 2016 | 55 | 2016 |
| Multiclass learnability and the erm principle A Daniely, S Sabato, S Ben-David, S Shalev-Shwartz The Journal of Machine Learning Research 16 (1), 2377-2404, 2015 | 51 | 2015 |
| Strongly adaptive online learning A Daniely, A Gonen, S Shalev-Shwartz International Conference on Machine Learning, 1405-1411, 2015 | 47 | 2015 |
| SGD learns the conjugate kernel class of the network A Daniely Advances in Neural Information Processing Systems, 2422-2430, 2017 | 43 | 2017 |
| On the practically interesting instances of MAXCUT Y Bilu, A Daniely, N Linial, M Saks arXiv preprint arXiv:1205.4893, 2012 | 33 | 2012 |
| Clustering is difficult only when it does not matter A Daniely, N Linial, M Saks arXiv preprint arXiv:1205.4891, 2012 | 33 | 2012 |
| Optimal learners for multiclass problems A Daniely, S Shalev-Shwartz arXiv preprint arXiv:1405.2420, 2014 | 30 | 2014 |
| More data speeds up training time in learning halfspaces over sparse vectors A Daniely, N Linial, S Shalev-Shwartz Advances in Neural Information Processing Systems, 145-153, 2013 | 29 | 2013 |
| Multiclass learning approaches: A theoretical comparison with implications A Daniely, S Sabato, SS Shwartz Advances in Neural Information Processing Systems, 485-493, 2012 | 25 | 2012 |
| Learning economic parameters from revealed preferences MF Balcan, A Daniely, R Mehta, R Urner, VV Vazirani International Conference on Web and Internet Economics, 338-353, 2014 | 23 | 2014 |
| A PTAS for agnostically learning halfspaces A Daniely Conference on Learning Theory, 484-502, 2015 | 20 | 2015 |
| Depth separation for neural networks A Daniely arXiv preprint arXiv:1702.08489, 2017 | 14 | 2017 |
| Inapproximability of truthful mechanisms via generalizations of the VC dimension A Daniely, M Schapira, G Shahaf Proceedings of the forty-seventh annual ACM symposium on Theory of Computing …, 2015 | 14 | 2015 |
| The complexity of learning halfspaces using generalized linear methods A Daniely, N Linial, S Shalev-Shwartz arXiv preprint arXiv:1211.0616, 2012 | 11 | 2012 |
| The price of bandit information in multiclass online classification A Daniely, T Helbertal Conference on Learning Theory, 93-104, 2013 | 7 | 2013 |
| Learning without interaction requires separation A Daniely, V Feldman arXiv preprint arXiv:1809.09165, 2018 | 6 | 2018 |
| Random features for compositional kernels A Daniely, R Frostig, V Gupta, Y Singer arXiv preprint arXiv:1703.07872, 2017 | 6 | 2017 |
Shai Shalev-ShwartzThe Hebrew UniversityVerified email at cs.huji.ac.il