Follow
Hanie Sedghi
Hanie Sedghi
Senior Research Scientist, Google Brain
Verified email at google.com - Homepage
Title
Cited by
Cited by
Year
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
2182015
The Singular Values of Convolutional Layers
H Sedghi, V Gupta, PM Long
arXiv preprint arXiv:1805.10408, 2018
1322018
What is being transferred in transfer learning?
B Neyshabur, H Sedghi, C Zhang
Neural Information Processing Systems (NeurIPS), 2020
1002020
Provable tensor methods for learning mixtures of generalized linear models
H Sedghi, M Janzamin, A Anandkumar
Artificial Intelligence and Statistics, 1223-1231, 2016
762016
Provable Methods for Training Neural Networks with Sparse Connectivity
H Sedghi, A Anandkumar
arXiv preprint arXiv:1412.2693, 2014
722014
Statistical Structure Learning to Ensure Data Integrity in Smart Grid
H Sedghi, E Jonckheere
IEEE Transactions on Smart Grid 6 (4), 1924-1933, 2015
552015
Score Function Features for Discriminative Learning: Matrix and Tensor Framework
M Janzamin, H Sedghi, A Anandkumar
arXiv preprint arXiv:1412.2863, 2014
392014
Statistical structure learning of smart grid for detection of false data injection
H Sedghi, E Jonckheere
2013 IEEE Power & Energy Society General Meeting, 1-5, 2013
392013
Generalization bounds for deep convolutional neural networks
PM Long, H Sedghi
International Conference on Learning Representations, 2020
342020
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
272010
The intriguing role of module criticality in the generalization of deep networks
NS Chatterji, B Neyshabur, H Sedghi
International Conference on Learning Representations, 2020
212020
Generalization bounds for neural networks through tensor factorization
M Janzamin, H Sedghi, A Anandkumar
CoRR, abs/1506.08473 1, 2015
202015
Training Input-Output Recurrent Neural Networks through Spectral Methods
H Sedghi, A Anandkumar
arXiv preprint arXiv:1603.00954, 2016
192016
Sysml: The new frontier of machine learning systems
A Ratner, D Alistarh, G Alonso, DG Andersen, P Bailis, S Bird, N Carlini, ...
172019
Multi-step stochastic ADMM in high dimensions: Applications to sparse optimization and matrix decomposition
H Sedghi, A Anandkumar, E Jonckheere
Advances in neural information processing systems 3 (January), 2771-2779, 2014
172014
The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers
P Nakkiran, B Neyshabur, H Sedghi
International Conference on Learning Representations, 2021
16*2021
Size-free generalization bounds for convolutional neural networks
PM Long, H Sedghi
162019
Learning Mixed Membership Community Models in Social Tagging Networks through Tensor Methods
A Anandkumar, H Sedghi
arXiv preprint arXiv:1503.04567, 2015
142015
Provable tensor methods for learning mixtures of classifiers
H Sedghi, A Anandkumar
arXiv preprint arXiv:1412.3046, 2014
142014
Exploring the Limits of Large Scale Pre-training
S Abnar, M Dehghani, B Neyshabur, H Sedghi
International Conference on Learning Representations, 2022
132022
The system can't perform the operation now. Try again later.
Articles 1–20