DeepAI
Log In Sign Up

Oops I Took A Gradient: Scalable Sampling for Discrete Distributions

02/08/2021
by   Will Grathwohl, et al.
2

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.

READ FULL TEXT

page 5

page 8

page 16

page 18

page 19

page 20

page 21

06/20/2022

A Langevin-like Sampler for Discrete Distributions

We propose discrete Langevin proposal (DLP), a simple and scalable gradi...
11/10/2020

Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration

Discrete structures play an important role in applications like program ...
08/20/2017

Boltzmann machines and energy-based models

We review Boltzmann machines and energy-based models. A Boltzmann machin...
06/02/2011

Restricted Collapsed Draw: Accurate Sampling for Hierarchical Chinese Restaurant Process Hidden Markov Models

We propose a restricted collapsed draw (RCD) sampler, a general Markov c...
06/15/2021

Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descent

We focus on the problem of efficient sampling and learning of probabilit...
06/29/2022

Discrete Langevin Sampler via Wasserstein Gradient Flow

Recently, a family of locally balanced (LB) samplers has demonstrated ex...
02/25/2012

Training Restricted Boltzmann Machines on Word Observations

The restricted Boltzmann machine (RBM) is a flexible tool for modeling c...