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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

MCTensor: A High-Precision Deep Learning Library with Multi-Component Floating-Point


Jul 18, 2022
Tao Yu, Went Guo, Jianan Canal Li, Tiancheng Yuan, Christopher De Sa

Add code

* HATE2022 in ICML2022 

   Access Paper or Ask Questions

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

Non-Determinism and the Lawlessness of ML Code


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

Add code


   Access Paper or Ask Questions

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

Low-Precision Stochastic Gradient Langevin Dynamics


Jun 20, 2022
Ruqi Zhang, Andrew Gordon Wilson, Christopher De Sa

Add code

* Published at ICML 2022 

   Access Paper or Ask Questions

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

GraB: Finding Provably Better Data Permutations than Random Reshuffling


May 22, 2022
Yucheng Lu, Wentao Guo, Christopher De Sa

Add code


   Access Paper or Ask Questions

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

Structured Pruning is All You Need for Pruning CNNs at Initialization


Mar 04, 2022
Yaohui Cai, Weizhe Hua, Hongzheng Chen, G. Edward Suh, Christopher De Sa, Zhiru Zhang

Add code


   Access Paper or Ask Questions

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

HyLa: Hyperbolic Laplacian Features For Graph Learning


Feb 14, 2022
Tao Yu, Christopher De Sa

Add code


   Access Paper or Ask Questions

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

Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam


Feb 12, 2022
Yucheng Lu, Conglong Li, Minjia Zhang, Christopher De Sa, Yuxiong He

Add code


   Access Paper or Ask Questions

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

Understanding Hyperdimensional Computing for Parallel Single-Pass Learning


Feb 10, 2022
Tao Yu, Yichi Zhang, Zhiru Zhang, Christopher De Sa

Add code


   Access Paper or Ask Questions

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

Tecnologica cosa: Modeling Storyteller Personalities in Boccaccio's Decameron


Sep 22, 2021
A. Feder Cooper, Maria Antoniak, Christopher De Sa, Marilyn Migiel, David Mimno

Add code

* The 5th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (co-located with EMNLP 2021) 

   Access Paper or Ask Questions

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

Equivariant Manifold Flows


Jul 19, 2021
Isay Katsman, Aaron Lou, Derek Lim, Qingxuan Jiang, Ser-Nam Lim, Christopher De Sa

Add code

* Preprint 

   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
4
5
6
>>