Transport Monte Carlo: High-Accuracy Posterior Approximation via Random Transport

TL;DR

This paper introduces a novel optimization-based method using random transport plans to achieve high-accuracy posterior sampling in Bayesian models, outperforming traditional MCMC and variational methods.

Contribution

It proposes a new approach to approximate the posterior distribution via a joint distribution with a simple uniform, enabling independent high-accuracy samples with theoretical guarantees.

Findings

Outperforms MCMC and variational Bayes in accuracy and speed

Effective in sampling multi-modal and high-dimensional distributions

Provides theoretical guarantees for approximation quality

Abstract

In Bayesian applications, there is a huge interest in rapid and accurate estimation of the posterior distribution, particularly for high dimensional or hierarchical models. In this article, we propose to use optimization to solve for a joint distribution (random transport plan) between two random variables, $\theta$ from the posterior distribution and $\beta$ from the simple multivariate uniform. Specifically, we obtain an approximate estimate of the conditional distribution $\Pi(\beta\mid \theta)$ as an infinite mixture of simple location-scale changes; applying the Bayes' theorem, $\Pi(\theta\mid\beta)$ can be sampled as one of the reversed transforms from the uniform, with the weight proportional to the posterior density/mass function. This produces independent random samples with high approximation accuracy, as well as nice theoretic guarantees. Our method shows compelling advantages in performance and accuracy, compared to the state-of-the-art Markov chain Monte Carlo and approximations such as variational Bayes and normalizing flow. We illustrate this approach via several challenging applications, such as sampling from multi-modal distribution, estimating sparse signals in high dimension, and soft-thresholding of a graph with a prior on the degrees.