Markov chain Monte Carlo for computing rare-event probabilities for a heavy-tailed random walk

TL;DR

This paper introduces an MCMC-based method to accurately estimate the probability of rare events in heavy-tailed random walks, providing an unbiased estimator with asymptotically vanishing variance.

Contribution

It develops a general MCMC algorithm for rare-event probability estimation and extends it to random sums, outperforming existing importance sampling methods.

Findings

Unbiased estimator with asymptotically vanishing normalized variance.

Effective for heavy-tailed random walks exceeding high thresholds.

Numerical results show improved performance over existing algorithms.

Abstract

In this paper a method based on a Markov chain Monte Carlo (MCMC) algorithm is proposed to compute the probability of a rare event. The conditional distribution of the underlying process given that the rare event occurs has the probability of the rare event as its normalizing constant. Using the MCMC methodology a Markov chain is simulated, with that conditional distribution as its invariant distribution, and information about the normalizing constant is extracted from its trajectory. The algorithm is described in full generality and applied to the problem of computing the probability that a heavy-tailed random walk exceeds a high threshold. An unbiased estimator of the reciprocal probability is constructed whose normalized variance vanishes asymptotically. The algorithm is extended to random sums and its performance is illustrated numerically and compared to existing importance sampling algorithms.