Matus Telgarsky
Matus Telgarsky
Verified email at illinois.edu - Homepage
Title
Cited by
Cited by
Year
Tensor decompositions for learning latent variable models
A Anandkumar, R Ge, D Hsu, SM Kakade, M Telgarsky
Journal of Machine Learning Research 15, 2773-2832, 2014
7922014
Spectrally-normalized margin bounds for neural networks
PL Bartlett, DJ Foster, MJ Telgarsky
Advances in Neural Information Processing Systems, 6240-6249, 2017
3342017
Benefits of depth in neural networks
M Telgarsky
arXiv preprint arXiv:1602.04485, 2016
2402016
Non-convex learning via stochastic gradient Langevin dynamics: a nonasymptotic analysis
M Raginsky, A Rakhlin, M Telgarsky
arXiv preprint arXiv:1702.03849, 2017
1482017
Representation benefits of deep feedforward networks
M Telgarsky
arXiv preprint arXiv:1509.08101, 2015
1022015
Hartigan’s method: k-means clustering without voronoi
M Telgarsky, A Vattani
Proceedings of the Thirteenth International Conference on Artificial …, 2010
722010
The implicit bias of gradient descent on nonseparable data
Z Ji, M Telgarsky
Conference on Learning Theory, 1772-1798, 2019
45*2019
Gradient descent aligns the layers of deep linear networks
Z Ji, M Telgarsky
arXiv preprint arXiv:1810.02032, 2018
362018
Agglomerative bregman clustering
M Telgarsky, S Dasgupta
arXiv preprint arXiv:1206.6446, 2012
292012
Neural networks and rational functions
M Telgarsky
Proceedings of the 34th International Conference on Machine Learning-Volume …, 2017
282017
Margins, shrinkage, and boosting
M Telgarsky
arXiv preprint arXiv:1303.4172, 2013
242013
A primal-dual convergence analysis of boosting
M Telgarsky
Journal of Machine Learning Research 13 (Mar), 561-606, 2012
222012
Tensor decompositions for learning latent variable models (A survey for ALT)
A Anandkumar, R Ge, D Hsu, SM Kakade, M Telgarsky
International Conference on Algorithmic Learning Theory, 19-38, 2015
142015
Moment-based Uniform Deviation Bounds for -means and Friends
MJ Telgarsky, S Dasgupta
Advances in Neural Information Processing Systems, 2940-2948, 2013
142013
Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks
Z Ji, M Telgarsky
arXiv preprint arXiv:1909.12292, 2019
102019
Dirichlet draws are sparse with high probability
M Telgarsky
arXiv preprint arXiv:1301.4917, 2013
92013
Convex risk minimization and conditional probability estimation
M Telgarsky, M Dudik, R Schapire
arXiv preprint arXiv:1506.04513, 2015
62015
Boosting with the logistic loss is consistent
M Telgarsky
arXiv preprint arXiv:1305.2648, 2013
52013
Greedy bi-criteria approximations for -medians and -means
D Hsu, M Telgarsky
arXiv preprint arXiv:1607.06203, 2016
42016
Scalable non-linear learning with adaptive polynomial expansions
A Agarwal, A Beygelzimer, DJ Hsu, J Langford, MJ Telgarsky
Advances in Neural Information Processing Systems, 2051-2059, 2014
42014
The system can't perform the operation now. Try again later.
Articles 1–20