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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Practical tradeoffs between memory, compute, and performance in learned optimizers


Apr 01, 2022
Luke Metz, C. Daniel Freeman, James Harrison, Niru Maheswaranathan, Jascha Sohl-Dickstein


   Access Paper or Ask Questions

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

Gradients are Not All You Need


Nov 10, 2021
Luke Metz, C. Daniel Freeman, Samuel S. Schoenholz, Tal Kachman


   Access Paper or Ask Questions

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

Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation


Jun 24, 2021
C. Daniel Freeman, Erik Frey, Anton Raichuk, Sertan Girgin, Igor Mordatch, Olivier Bachem

* 9 pages + 12 pages of appendices and references. In submission at NeurIPS 2021 Datasets and Benchmarks Track 

   Access Paper or Ask Questions

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

Training Learned Optimizers with Randomly Initialized Learned Optimizers


Jan 14, 2021
Luke Metz, C. Daniel Freeman, Niru Maheswaranathan, Jascha Sohl-Dickstein


   Access Paper or Ask Questions

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

Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves


Sep 23, 2020
Luke Metz, Niru Maheswaranathan, C. Daniel Freeman, Ben Poole, Jascha Sohl-Dickstein


   Access Paper or Ask Questions

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

Using a thousand optimization tasks to learn hyperparameter search strategies


Mar 11, 2020
Luke Metz, Niru Maheswaranathan, Ruoxi Sun, C. Daniel Freeman, Ben Poole, Jascha Sohl-Dickstein


   Access Paper or Ask Questions

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

Learning to Predict Without Looking Ahead: World Models Without Forward Prediction


Oct 31, 2019
C. Daniel Freeman, Luke Metz, David Ha

* To appear at the Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019) 

   Access Paper or Ask Questions

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

Learned optimizers that outperform SGD on wall-clock and test loss


Oct 26, 2018
Luke Metz, Niru Maheswaranathan, Jeremy Nixon, C. Daniel Freeman, Jascha Sohl-Dickstein


   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
>>