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 Will Grathwohl

Oops I Took A Gradient: Scalable Sampling for Discrete Distributions


Feb 08, 2021
Will Grathwohl, Kevin Swersky, Milad Hashemi, David Duvenaud, Chris J. Maddison

* Energy-Based Models, Deep generative models, MCMC sampling 

  Access Paper or Ask Questions

No MCMC for me: Amortized sampling for fast and stable training of energy-based models


Oct 14, 2020
Will Grathwohl, Jacob Kelly, Milad Hashemi, Mohammad Norouzi, Kevin Swersky, David Duvenaud


  Access Paper or Ask Questions

Cutting out the Middle-Man: Training and Evaluating Energy-Based Models without Sampling


Feb 14, 2020
Will Grathwohl, Kuan-Chieh Wang, Jorn-Henrik Jacobsen, David Duvenaud, Richard Zemel


  Access Paper or Ask Questions

Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One


Dec 11, 2019
Will Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud, Mohammad Norouzi, Kevin Swersky


  Access Paper or Ask Questions

FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models


Oct 22, 2018
Will Grathwohl, Ricky T. Q. Chen, Jesse Bettencourt, Ilya Sutskever, David Duvenaud

* 8 Pages, 6 figures 

  Access Paper or Ask Questions

Backpropagation through the Void: Optimizing control variates for black-box gradient estimation


Feb 23, 2018
Will Grathwohl, Dami Choi, Yuhuai Wu, Geoffrey Roeder, David Duvenaud

* Published at ICLR 2018 

  Access Paper or Ask Questions

Disentangling Space and Time in Video with Hierarchical Variational Auto-encoders


Dec 19, 2016
Will Grathwohl, Aaron Wilson

* fixed typo in equation 16 

  Access Paper or Ask Questions