Beating the perils of non-convexity: Guaranteed training of neural networks using tensor methods M Janzamin, H Sedghi, A Anandkumar
arXiv preprint arXiv:1506.08473, 2015
287 2015 Guaranteed Non-Orthogonal Tensor Decomposition via Alternating Rank- A Anandkumar, R Ge, M Janzamin
arXiv preprint arXiv:1402.5180, 2014
159 2014 Provable tensor methods for learning mixtures of generalized linear models H Sedghi, M Janzamin, A Anandkumar
Artificial Intelligence and Statistics, 1223-1231, 2016
111 2016 Learning overcomplete latent variable models through tensor methods A Anandkumar, R Ge, M Janzamin
Conference on Learning Theory, 36-112, 2015
62 2015 When are overcomplete topic models identifiable? uniqueness of tensor tucker decompositions with structured sparsity A Anandkumar, D Hsu, M Janzamin, S Kakade
The Journal of Machine Learning Research 16 (1), 2643-2694, 2015
61 2015 Analyzing tensor power method dynamics in overcomplete regime A Anandkumar, R Ge, M Janzamin
Journal of Machine Learning Research 18 (22), 1-40, 2017
56 2017 Spectral learning on matrices and tensors M Janzamin, R Ge, J Kossaifi, A Anandkumar
Foundations and Trends® in Machine Learning 12 (5-6), 393-536, 2019
54 2019 Score function features for discriminative learning: Matrix and tensor framework M Janzamin, H Sedghi, A Anandkumar
arXiv preprint arXiv:1412.2863, 2014
50 2014 Analyzing tensor power method dynamics: Applications to learning overcomplete latent variable models A Anandkumar, R Ge, M Janzamin
arXiv preprint arXiv:1411.1488 98, 2014
30 2014 Sample complexity analysis for learning overcomplete latent variable models through tensor methods A Anandkumar, R Ge, M Janzamin
arXiv preprint arXiv:1408.0553, 2014
30 * 2014 A game-theoretic approach for power allocation in bidirectional cooperative communication M Janzamin, MR Pakravan, H Sedghi
2010 IEEE Wireless Communication and Networking Conference, 1-6, 2010
30 2010 High-dimensional covariance decomposition into sparse Markov and independence models M Janzamin, A Anandkumar
The Journal of Machine Learning Research 15 (1), 1549-1591, 2014
11 2014 High-dimensional covariance decomposition into sparse Markov and independence domains M Janzamin, A Anandkumar
arXiv preprint arXiv:1206.6382, 2012
4 2012 Feast at play: Feature extraction using score function tensors M Janzamin, H Sedghi, UN Niranjan, A Anandkumar
Feature Extraction: Modern Questions and Challenges, 130-144, 2015
2 2015 Score function features for discriminative learning M Janzamin, H Sedghi, A Anandkumar
arXiv preprint arXiv:1412.6514, 2014
1 2014 Non-convex Optimization in Machine Learning: Provable Guarantees Using Tensor Methods M Janzamin
University of California, Irvine, 2016
2016 Matrix and Tensor Features for Discriminative Learning M Janzamin, H Sedghi, A Anandkumar
arXiv preprint arXiv:1412.2863, 2014
2014 Supplementary Material for the AISTATS 2016 Paper: Provable Tensor Methods for Learning Mixtures of Generalized Linear Models H Sedghi, M Janzamin, A Anandkumar
When are Overcomplete Representations Identifiable? Uniqueness of Tensor Decompositions Under Expansion Constraints A Anandkumar, D Hsu, M Janzamin, S Kakade
Anima AnandkumarCalifornia Institute of Technology and NVIDIAПотвърден имейл адрес: caltech.edu