Amit Daniely
Amit Daniely
mail.huji.ac.il üzerinde doğrulanmış e-posta adresine sahip - Ana Sayfa
Başlık
Alıntı yapanlar
Alıntı yapanlar
Yıl
Toward deeper understanding of neural networks: The power of initialization and a dual view on expressivity
A Daniely, R Frostig, Y Singer
arXiv preprint arXiv:1602.05897, 2016
2102016
SGD learns the conjugate kernel class of the network
A Daniely
arXiv preprint arXiv:1702.08503, 2017
1202017
Complexity theoretic limitations on learning DNF’s
A Daniely, S Shalev-Shwartz
Conference on Learning Theory, 815-830, 2016
972016
Complexity theoretic limitations on learning halfspaces
A Daniely
Proceedings of the forty-eighth annual ACM symposium on Theory of Computing …, 2016
952016
From average case complexity to improper learning complexity
A Daniely, N Linial, S Shalev-Shwartz
Proceedings of the forty-sixth annual ACM symposium on Theory of computing …, 2014
862014
Strongly adaptive online learning
A Daniely, A Gonen, S Shalev-Shwartz
International Conference on Machine Learning, 1405-1411, 2015
822015
Multiclass learnability and the erm principle
A Daniely, S Sabato, S Ben-David, S Shalev-Shwartz
Proceedings of the 24th Annual Conference on Learning Theory, 207-232, 2011
732011
Depth separation for neural networks
A Daniely
Conference on Learning Theory, 690-696, 2017
452017
More data speeds up training time in learning halfspaces over sparse vectors
A Daniely, N Linial, SS Shwartz
arXiv preprint arXiv:1311.2271, 2013
412013
Clustering is difficult only when it does not matter
A Daniely, N Linial, M Saks
arXiv preprint arXiv:1205.4891, 2012
392012
Optimal learners for multiclass problems
A Daniely, S Shalev-Shwartz
Conference on Learning Theory, 287-316, 2014
382014
Multiclass learning approaches: A theoretical comparison with implications
A Daniely, S Sabato, SS Shwartz
arXiv preprint arXiv:1205.6432, 2012
382012
A PTAS for agnostically learning halfspaces
A Daniely
Conference on Learning Theory, 484-502, 2015
372015
On the practically interesting instances of MAXCUT
Y Bilu, A Daniely, N Linial, M Saks
arXiv preprint arXiv:1205.4893, 2012
372012
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
342014
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
192015
The complexity of learning halfspaces using generalized linear methods
A Daniely, N Linial, S Shalev-Shwartz
Conference on Learning Theory, 244-286, 2014
142014
Neural networks learning and memorization with (almost) no over-parameterization
A Daniely
arXiv preprint arXiv:1911.09873, 2019
112019
Learning without interaction requires separation
A Daniely, V Feldman
arXiv preprint arXiv:1809.09165, 2018
92018
Random features for compositional kernels
A Daniely, R Frostig, V Gupta, Y Singer
arXiv preprint arXiv:1703.07872, 2017
92017
Sistem, işlemi şu anda gerçekleştiremiyor. Daha sonra yeniden deneyin.
Makaleler 1–20