Bounding Wasserstein distance with couplings

12/06/2021
by   Niloy Biswas, et al.
0

Markov chain Monte Carlo (MCMC) provides asymptotically consistent estimates of intractable posterior expectations as the number of iterations tends to infinity. However, in large data applications, MCMC can be computationally expensive per iteration. This has catalyzed interest in sampling methods such as approximate MCMC, which trade off asymptotic consistency for improved computational speed. In this article, we propose estimators based on couplings of Markov chains to assess the quality of such asymptotically biased sampling methods. The estimators give empirical upper bounds of the Wassertein distance between the limiting distribution of the asymptotically biased sampling method and the original target distribution of interest. We establish theoretical guarantees for our upper bounds and show that our estimators can remain effective in high dimensions. We apply our quality measures to stochastic gradient MCMC, variational Bayes, and Laplace approximations for tall data and to approximate MCMC for Bayesian logistic regression in 4500 dimensions and Bayesian linear regression in 50000 dimensions.

READ FULL TEXT

Authors

page 1

page 2

page 3

page 4

05/23/2019

Estimating Convergence of Markov chains with L-Lag Couplings

Markov chain Monte Carlo (MCMC) methods generate samples that are asympt...
08/11/2017

Unbiased Markov chain Monte Carlo with couplings

Markov chain Monte Carlo (MCMC) methods provide consistent approximation...
11/02/2019

Laplacian Smoothing Stochastic Gradient Markov Chain Monte Carlo

As an important Markov Chain Monte Carlo (MCMC) method, stochastic gradi...
05/04/2016

Multi Level Monte Carlo methods for a class of ergodic stochastic differential equations

We develop a framework that allows the use of the multi-level Monte Carl...
05/29/2020

Rate-optimal refinement strategies for local approximation MCMC

Many Bayesian inference problems involve target distributions whose dens...
01/28/2021

Low Complexity Approximate Bayesian Logistic Regression for Sparse Online Learning

Theoretical results show that Bayesian methods can achieve lower bounds ...
06/20/2020

Asymptotically Optimal Exact Minibatch Metropolis-Hastings

Metropolis-Hastings (MH) is a commonly-used MCMC algorithm, but it can b...

Code Repositories

BoundWasserstein

Bounding Wasserstein distance with couplings


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.