Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Hanie Sedghi

Hanie Sedghi

The Deep Bootstrap: Good Online Learners are Good Offline Generalizers


Oct 16, 2020
Preetum Nakkiran, Behnam Neyshabur, Hanie Sedghi

Figure 1 for The Deep Bootstrap: Good Online Learners are Good Offline Generalizers
Figure 2 for The Deep Bootstrap: Good Online Learners are Good Offline Generalizers
Figure 3 for The Deep Bootstrap: Good Online Learners are Good Offline Generalizers
Figure 4 for The Deep Bootstrap: Good Online Learners are Good Offline Generalizers

  Access Paper or Ask Questions

What is being transferred in transfer learning?


Aug 26, 2020
Behnam Neyshabur, Hanie Sedghi, Chiyuan Zhang

Figure 1 for What is being transferred in transfer learning?
Figure 2 for What is being transferred in transfer learning?
Figure 3 for What is being transferred in transfer learning?
Figure 4 for What is being transferred in transfer learning?
* Equal contribution, authors ordered randomly 
  Access Paper or Ask Questions

The intriguing role of module criticality in the generalization of deep networks


Dec 04, 2019
Niladri S. Chatterji, Behnam Neyshabur, Hanie Sedghi

Figure 1 for The intriguing role of module criticality in the generalization of deep networks
Figure 2 for The intriguing role of module criticality in the generalization of deep networks
Figure 3 for The intriguing role of module criticality in the generalization of deep networks
Figure 4 for The intriguing role of module criticality in the generalization of deep networks

  Access Paper or Ask Questions

Size-free generalization bounds for convolutional neural networks


Jun 12, 2019
Philip M. Long, Hanie Sedghi

Figure 1 for Size-free generalization bounds for convolutional neural networks
Figure 2 for Size-free generalization bounds for convolutional neural networks
Figure 3 for Size-free generalization bounds for convolutional neural networks
Figure 4 for Size-free generalization bounds for convolutional neural networks

  Access Paper or Ask Questions

SysML: The New Frontier of Machine Learning Systems


May 01, 2019
Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen, Peter Bailis, Sarah Bird, Nicholas Carlini, Bryan Catanzaro, Jennifer Chayes, Eric Chung, Bill Dally, Jeff Dean, Inderjit S. Dhillon, Alexandros Dimakis, Pradeep Dubey, Charles Elkan, Grigori Fursin, Gregory R. Ganger, Lise Getoor, Phillip B. Gibbons, Garth A. Gibson, Joseph E. Gonzalez, Justin Gottschlich, Song Han, Kim Hazelwood, Furong Huang, Martin Jaggi, Kevin Jamieson, Michael I. Jordan, Gauri Joshi, Rania Khalaf, Jason Knight, Jakub Konečný, Tim Kraska, Arun Kumar, Anastasios Kyrillidis, Aparna Lakshmiratan, Jing Li, Samuel Madden, H. Brendan McMahan, Erik Meijer, Ioannis Mitliagkas, Rajat Monga, Derek Murray, Kunle Olukotun, Dimitris Papailiopoulos, Gennady Pekhimenko, Theodoros Rekatsinas, Afshin Rostamizadeh, Christopher Ré, Christopher De Sa, Hanie Sedghi, Siddhartha Sen, Virginia Smith, Alex Smola, Dawn Song, Evan Sparks, Ion Stoica, Vivienne Sze, Madeleine Udell, Joaquin Vanschoren, Shivaram Venkataraman, Rashmi Vinayak, Markus Weimer, Andrew Gordon Wilson, Eric Xing, Matei Zaharia, Ce Zhang, Ameet Talwalkar


  Access Paper or Ask Questions

On the effect of the activation function on the distribution of hidden nodes in a deep network


Jan 07, 2019
Philip M. Long, Hanie Sedghi

Figure 1 for On the effect of the activation function on the distribution of hidden nodes in a deep network
Figure 2 for On the effect of the activation function on the distribution of hidden nodes in a deep network

  Access Paper or Ask Questions

The Singular Values of Convolutional Layers


May 26, 2018
Hanie Sedghi, Vineet Gupta, Philip M. Long

Figure 1 for The Singular Values of Convolutional Layers
Figure 2 for The Singular Values of Convolutional Layers
Figure 3 for The Singular Values of Convolutional Layers
Figure 4 for The Singular Values of Convolutional Layers

  Access Paper or Ask Questions

Knowledge Completion for Generics using Guided Tensor Factorization


Mar 28, 2018
Hanie Sedghi, Ashish Sabharwal

* To appear in TACL 
  Access Paper or Ask Questions

Training Input-Output Recurrent Neural Networks through Spectral Methods


Oct 31, 2016
Hanie Sedghi, Anima Anandkumar

Figure 1 for Training Input-Output Recurrent Neural Networks through Spectral Methods
Figure 2 for Training Input-Output Recurrent Neural Networks through Spectral Methods

  Access Paper or Ask Questions

Provable Tensor Methods for Learning Mixtures of Generalized Linear Models


Jan 13, 2016
Hanie Sedghi, Majid Janzamin, Anima Anandkumar

* To appear in Proceeding of AI and Statistics (AISTATS) 2016 
  Access Paper or Ask Questions

Beating the Perils of Non-Convexity: Guaranteed Training of Neural Networks using Tensor Methods


Jan 12, 2016
Majid Janzamin, Hanie Sedghi, Anima Anandkumar

Figure 1 for Beating the Perils of Non-Convexity: Guaranteed Training of Neural Networks using Tensor Methods
Figure 2 for Beating the Perils of Non-Convexity: Guaranteed Training of Neural Networks using Tensor Methods
* The tensor decomposition analysis is expanded, and the analysis of ridge regression is added for recovering the parameters of last layer of neural network 
  Access Paper or Ask Questions

Multi-Step Stochastic ADMM in High Dimensions: Applications to Sparse Optimization and Noisy Matrix Decomposition


Jul 07, 2015
Hanie Sedghi, Anima Anandkumar, Edmond Jonckheere

Figure 1 for Multi-Step Stochastic ADMM in High Dimensions: Applications to Sparse Optimization and Noisy Matrix Decomposition
Figure 2 for Multi-Step Stochastic ADMM in High Dimensions: Applications to Sparse Optimization and Noisy Matrix Decomposition
Figure 3 for Multi-Step Stochastic ADMM in High Dimensions: Applications to Sparse Optimization and Noisy Matrix Decomposition
* appeared in Neural Information Processing Systems(NIPS) 2014. arXiv admin note: text overlap with arXiv:1207.4421 by other authors 
  Access Paper or Ask Questions

Provable Methods for Training Neural Networks with Sparse Connectivity


Apr 28, 2015
Hanie Sedghi, Anima Anandkumar

Figure 1 for Provable Methods for Training Neural Networks with Sparse Connectivity
* Accepted for presentation at Neural Information Processing Systems(NIPS) 2014 Deep Learning workshop and Accepted as a workshop contribution at ICLR 2015 
  Access Paper or Ask Questions

Learning Mixed Membership Community Models in Social Tagging Networks through Tensor Methods


Apr 22, 2015
Anima Anandkumar, Hanie Sedghi

Figure 1 for Learning Mixed Membership Community Models in Social Tagging Networks through Tensor Methods
Figure 2 for Learning Mixed Membership Community Models in Social Tagging Networks through Tensor Methods

  Access Paper or Ask Questions

Score Function Features for Discriminative Learning


Apr 19, 2015
Majid Janzamin, Hanie Sedghi, Anima Anandkumar

Figure 1 for Score Function Features for Discriminative Learning
* Accepted as a workshop contribution at ICLR 2015. A longer version of this work is also available on arXiv: http://arxiv.org/abs/1412.2863 
  Access Paper or Ask Questions

Score Function Features for Discriminative Learning: Matrix and Tensor Framework


Dec 11, 2014
Majid Janzamin, Hanie Sedghi, Anima Anandkumar

Figure 1 for Score Function Features for Discriminative Learning: Matrix and Tensor Framework
* 29 pages 
  Access Paper or Ask Questions

Statistical Structure Learning, Towards a Robust Smart Grid


Mar 07, 2014
Hanie Sedghi, Edmond Jonckheere

Figure 1 for Statistical Structure Learning, Towards a Robust Smart Grid
Figure 2 for Statistical Structure Learning, Towards a Robust Smart Grid
Figure 3 for Statistical Structure Learning, Towards a Robust Smart Grid
Figure 4 for Statistical Structure Learning, Towards a Robust Smart Grid

  Access Paper or Ask Questions