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 Soham De

A study on the plasticity of neural networks


May 31, 2021
Tudor Berariu, Wojciech Czarnecki, Soham De, Jorg Bornschein, Samuel Smith, Razvan Pascanu, Claudia Clopath


  Access Paper or Ask Questions

Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error


May 27, 2021
Stanislav Fort, Andrew Brock, Razvan Pascanu, Soham De, Samuel L. Smith


  Access Paper or Ask Questions

High-Performance Large-Scale Image Recognition Without Normalization


Feb 11, 2021
Andrew Brock, Soham De, Samuel L. Smith, Karen Simonyan


  Access Paper or Ask Questions

On the Origin of Implicit Regularization in Stochastic Gradient Descent


Jan 28, 2021
Samuel L. Smith, Benoit Dherin, David G. T. Barrett, Soham De

* Accepted as a conference paper at ICLR 2021 

  Access Paper or Ask Questions

Characterizing signal propagation to close the performance gap in unnormalized ResNets


Jan 27, 2021
Andrew Brock, Soham De, Samuel L. Smith

* Published as a conference paper at ICLR 2021 

  Access Paper or Ask Questions

BYOL works even without batch statistics


Oct 20, 2020
Pierre H. Richemond, Jean-Bastien Grill, Florent Altché, Corentin Tallec, Florian Strub, Andrew Brock, Samuel Smith, Soham De, Razvan Pascanu, Bilal Piot, Michal Valko


  Access Paper or Ask Questions

On the Generalization Benefit of Noise in Stochastic Gradient Descent


Jun 26, 2020
Samuel L. Smith, Erich Elsen, Soham De

* Camera-ready version of ICML 2020 

  Access Paper or Ask Questions

Batch Normalization Biases Deep Residual Networks Towards Shallow Paths


Feb 24, 2020
Soham De, Samuel L. Smith


  Access Paper or Ask Questions

Adversarial Robustness through Local Linearization


Jul 04, 2019
Chongli Qin, James Martens, Sven Gowal, Dilip Krishnan, Krishnamurthy, Dvijotham, Alhussein Fawzi, Soham De, Robert Stanforth, Pushmeet Kohli


  Access Paper or Ask Questions

The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent


Apr 15, 2019
Karthik A. Sankararaman, Soham De, Zheng Xu, W. Ronny Huang, Tom Goldstein


  Access Paper or Ask Questions

Convergence guarantees for RMSProp and ADAM in non-convex optimization and an empirical comparison to Nesterov acceleration


Oct 08, 2018
Soham De, Anirbit Mukherjee, Enayat Ullah

* Presented on 14th July 2018 at the ICML Workshop on Modern Trends in Nonconvex Optimization for Machine Learning 

  Access Paper or Ask Questions

Training Quantized Nets: A Deeper Understanding


Nov 13, 2017
Hao Li, Soham De, Zheng Xu, Christoph Studer, Hanan Samet, Tom Goldstein

* NIPS 2017 

  Access Paper or Ask Questions

Variance Reduction for Distributed Stochastic Gradient Descent


Apr 07, 2017
Soham De, Gavin Taylor, Tom Goldstein


  Access Paper or Ask Questions

Efficient Distributed SGD with Variance Reduction


Apr 07, 2017
Soham De, Tom Goldstein

* In Proceedings of 2016 IEEE International Conference on Data Mining (ICDM) 

  Access Paper or Ask Questions

Big Batch SGD: Automated Inference using Adaptive Batch Sizes


Apr 06, 2017
Soham De, Abhay Yadav, David Jacobs, Tom Goldstein

* A preliminary version of this paper appears in AISTATS 2017 (International Conference on Artificial Intelligence and Statistics) 

  Access Paper or Ask Questions

Son of Zorn's Lemma: Targeted Style Transfer Using Instance-aware Semantic Segmentation


Jan 09, 2017
Carlos Castillo, Soham De, Xintong Han, Bharat Singh, Abhay Kumar Yadav, Tom Goldstein

* ICASSP 2017 

  Access Paper or Ask Questions

An Empirical Study of ADMM for Nonconvex Problems


Dec 10, 2016
Zheng Xu, Soham De, Mario Figueiredo, Christoph Studer, Tom Goldstein

* NIPS nonconvex workshop 

  Access Paper or Ask Questions

Layer-Specific Adaptive Learning Rates for Deep Networks


Oct 15, 2015
Bharat Singh, Soham De, Yangmuzi Zhang, Thomas Goldstein, Gavin Taylor

* ICMLA 2015, deep learning, adaptive learning rates for training, layer specific learning rate 

  Access Paper or Ask Questions

Plagiarism Detection in Polyphonic Music using Monaural Signal Separation


Feb 27, 2015
Soham De, Indradyumna Roy, Tarunima Prabhakar, Kriti Suneja, Sourish Chaudhuri, Rita Singh, Bhiksha Raj

* INTERSPEECH-2012, 1744-1747 (2012) 
* Preprint version 

  Access Paper or Ask Questions