Improved Bounds for Context-Dependent Evolutionary Models Using Sequential Monte Carlo

TL;DR

This paper introduces an efficient sequential Monte Carlo algorithm with proven mixing time bounds for approximating marginal likelihoods in complex evolutionary models with site dependence, improving over previous importance sampling methods.

Contribution

It develops a novel SMC algorithm with theoretical mixing bounds for dependent-site evolutionary models, enhancing computational efficiency and accuracy.

Findings

The SMC algorithm provides a polynomial mixing time bound.

It achieves more accurate marginal likelihood estimates than previous importance samplers.

The approach is potentially applicable to other Bayesian inference problems.

Abstract

Statistical inference in evolutionary models with site-dependence is a long-standing challenge in phylogenetics and computational biology. We consider the problem of approximating marginal sequence likelihoods under dependent-site models of biological sequence evolution. We prove a polynomial mixing time bound for a Markov chain Monte Carlo algorithm that samples the conditional distribution over latent sample paths, when the chain is initialized with a warm start. We then introduce a sequential Monte Carlo (SMC) algorithm for approximating the marginal likelihood, and show that our mixing time bound can be combined with recent importance sampling and finite-sample SMC results to obtain bounds on the finite sample approximation error of the resulting estimator. Our results show that the proposed SMC algorithm yields an efficient randomized approximation scheme for many practical problems of interest, and offers a significant improvement over a recently developed importance sampler for this problem. Our approach combines recent innovations in obtaining bounds for MCMC and SMC samplers, and may prove applicable to other problems of approximating marginal likelihoods and Bayes factors.