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]

@inproceedings{GrathwohlKH0SD21,
  title = {No MCMC for me: Amortized sampling for fast and stable training of energy-based models},
  author = {Will Sussman Grathwohl and Jacob Jin Kelly and Milad Hashemi and Mohammad Norouzi 0002 and Kevin Swersky and David Duvenaud},
  year = {2021},
  url = {https://openreview.net/forum?id=ixpSxO9flk3},
  researchr = {https://researchr.org/publication/GrathwohlKH0SD21},
  cites = {0},
  citedby = {0},
  booktitle = {9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021},
  publisher = {OpenReview.net},
}