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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Non-Determinism and the Lawlessness of ML Code


Jun 23, 2022
A. Feder Cooper, Jonathan Frankle, Christopher De Sa


   Access Paper or Ask Questions

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

Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks


Jun 02, 2022
Mansheej Paul, Brett W. Larsen, Surya Ganguli, Jonathan Frankle, Gintare Karolina Dziugaite

* The first two authors contributed equally 

   Access Paper or Ask Questions

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

Fast Benchmarking of Accuracy vs. Training Time with Cyclic Learning Rates


Jun 02, 2022
Jacob Portes, Davis Blalock, Cory Stephenson, Jonathan Frankle

* 8 pages, 7 figures 

   Access Paper or Ask Questions

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

Strengthening Subcommunities: Towards Sustainable Growth in AI Research


Apr 18, 2022
Andi Peng, Jessica Zosa Forde, Yonadav Shavit, Jonathan Frankle

* ICLR 2022 ML Evaluation Standards Workshop 

   Access Paper or Ask Questions

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

Trade-offs of Local SGD at Scale: An Empirical Study


Oct 15, 2021
Jose Javier Gonzalez Ortiz, Jonathan Frankle, Mike Rabbat, Ari Morcos, Nicolas Ballas


   Access Paper or Ask Questions

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

What can linear interpolation of neural network loss landscapes tell us?


Jun 30, 2021
Tiffany Vlaar, Jonathan Frankle


   Access Paper or Ask Questions

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

Studying the Consistency and Composability of Lottery Ticket Pruning Masks


Apr 30, 2021
Rajiv Movva, Jonathan Frankle, Michael Carbin

* Workshop on Science and Engineering of Deep Learning (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

The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models


Dec 12, 2020
Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Michael Carbin, Zhangyang Wang


   Access Paper or Ask Questions

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

Revisiting "Qualitatively Characterizing Neural Network Optimization Problems"


Dec 12, 2020
Jonathan Frankle

* Workshop on Deep Learning and Information Geometry (NeurIPS 2020) 

   Access Paper or Ask Questions

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

Are all negatives created equal in contrastive instance discrimination?


Oct 25, 2020
Tiffany Tianhui Cai, Jonathan Frankle, David J. Schwab, Ari S. Morcos

* Fixed author name error 

   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
3
>>