DeepAI AI Chat
Log In Sign Up

Finite Sample Complexity of Sequential Monte Carlo Estimators on Multimodal Target Distributions

08/13/2022
by   Joseph Mathews, et al.
Duke University
0

We prove finite sample complexities for sequential Monte Carlo (SMC) algorithms which require only local mixing times of the associated Markov kernels. Our bounds are particularly useful when the target distribution is multimodal and global mixing of the Markov kernel is slow; in such cases our approach establishes the benefits of SMC over the corresponding Markov chain Monte Carlo (MCMC) estimator. The lack of global mixing is addressed by sequentially controlling the bias introduced by SMC resampling procedures. We apply these results to obtain complexity bounds for approximating expectations under mixtures of log-concave distributions and show that SMC provides a fully polynomial time randomized approximation scheme for some difficult multimodal problems where the corresponding Markov chain sampler is exponentially slow. Finally, we compare the bounds obtained by our approach to existing bounds for tempered Markov chains on the same problems.

READ FULL TEXT

page 1

page 2

page 3

page 4

03/25/2018

Finite Sample Complexity of Sequential Monte Carlo Estimators

We present bounds for the finite sample error of sequential Monte Carlo ...
03/22/2022

Bounds on Wasserstein distances between continuous distributions using independent samples

The plug-in estimator of the Wasserstein distance is known to be conserv...
07/03/2018

Finite Sample L_2 Bounds for Sequential Monte Carlo and Adaptive Path Selection

We prove a bound on the finite sample error of sequential Monte Carlo (S...
11/25/2022

Toward Unlimited Self-Learning Monte Carlo with Annealing Process Using VAE's Implicit Isometricity

Self-learning Monte Carlo (SLMC) methods are recently proposed to accele...
11/21/2016

Measuring Sample Quality with Diffusions

Standard Markov chain Monte Carlo diagnostics, like effective sample siz...
08/03/2020

The Amazing Power of Randomness: NP=RP

We (claim to) prove the extremely surprising fact that NP=RP. It is achi...