Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
Abstract
We propose a general and scalable approximate sampling strategy for probabilistic models with discrete variables. Our approach uses gradients of the likelihood function with respect to its discrete inputs to propose updates in a Metropolis-Hastings sampler. We show empirically that this approach outperforms generic samplers in a number of difficult settings including Ising models, Potts models, restricted Boltzmann machines, and factorial hidden Markov models. We also demonstrate the use of our improved sampler for training deep energy-based models on high dimensional discrete data. This approach outperforms variational auto-encoders and existing energy-based models. Finally, we give bounds showing that our approach is near-optimal in the class of samplers which propose local updates.
Cite
@article{arxiv.2102.04509,
title = {Oops I Took A Gradient: Scalable Sampling for Discrete Distributions},
author = {Will Grathwohl and Kevin Swersky and Milad Hashemi and David Duvenaud and Chris J. Maddison},
journal= {arXiv preprint arXiv:2102.04509},
year = {2021}
}
Comments
Energy-Based Models, Deep generative models, MCMC sampling