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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Unlocking High-Accuracy Differentially Private Image Classification through Scale


Apr 28, 2022
Soham De, Leonard Berrada, Jamie Hayes, Samuel L. Smith, Borja Balle


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Cold Posteriors and Aleatoric Uncertainty


Jul 31, 2020
Ben Adlam, Jasper Snoek, Samuel L. Smith

* ICML workshop on Uncertainty and Robustness in Deep Learning (2020) 
* 5 pages, 3 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Batch Normalization Biases Deep Residual Networks Towards Shallow Paths


Feb 24, 2020
Soham De, Samuel L. Smith


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study


May 09, 2019
Daniel S. Park, Jascha Sohl-Dickstein, Quoc V. Le, Samuel L. Smith

* 17 pages, 3 tables, 17 figures; accepted to ICML 2019 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>