DeepAI AI Chat
Log In Sign Up

Unbiased Multilevel Monte Carlo methods for intractable distributions: MLMC meets MCMC

by   Guanyang Wang, et al.

Constructing unbiased estimators from Markov chain Monte Carlo (MCMC) outputs has recently increased much attention in statistics and machine learning communities. However, the existing unbiased MCMC framework only works when the quantity of interest is an expectation, which rules out many practical applications. In this paper, we propose a general method to construct unbiased estimators for function of expectations. We further generalize this method to estimate nested expectations. Our idea is based on the combination and generalization of the unbiased MCMC and Multilevel Monte Carlo (MLMC) methods. In contrast to traditional sequential methods, our estimator can be easily implemented on parallel processors independently. We prove our estimator has a finite variance, a finite computational complexity, and achieves ε-accuracy within O(1/ε^2) computational cost under mild conditions. We also illustrate our estimator on both synthetic and real data examples.


page 1

page 2

page 3

page 4


Unbiased Optimal Stopping via the MUSE

We propose a new unbiased estimator for estimating the utility of the op...

Invertible Flow Non Equilibrium sampling

Simultaneously sampling from a complex distribution with intractable nor...

Optimal randomized multilevel Monte Carlo for repeatedly nested expectations

The estimation of repeatedly nested expectations is a challenging task t...

Unbiased approximations of products of expectations

We consider the problem of approximating the product of n expectations w...

New Tricks for Estimating Gradients of Expectations

We derive a family of Monte Carlo estimators for gradients of expectatio...

Efficient Debiased Variational Bayes by Multilevel Monte Carlo Methods

Variational Bayes is a method to find a good approximation of the poster...

On Unbiased Estimation for Discretized Models

In this article, we consider computing expectations w.r.t. probability m...