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

Will Sussman Grathwohl, Jacob Jin Kelly, Milad Hashemi, Mohammad Norouzi 0002, Kevin Swersky, David Duvenaud. No MCMC for me: Amortized sampling for fast and stable training of energy-based models. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, 2021. [doi]

Abstract

Abstract is missing.