Advanced MCMC Methods for Sampling on Diffusion Pathspace

TL;DR

This paper introduces advanced MCMC algorithms, especially Hybrid Monte Carlo, for efficient sampling of complex diffusion path models in infinite-dimensional spaces, demonstrating mesh-free mixing times and computational advantages.

Contribution

It develops and analyzes advanced MCMC methods tailored for diffusion pathspace, improving sampling efficiency and convergence properties over traditional algorithms.

Findings

Advanced HMC achieves mesh-free mixing times.

Algorithms perform well in stochastic volatility and survival models.

Computational benefits shown through theoretical and experimental results.

Abstract

The need to calibrate increasingly complex statistical models requires a persistent effort for further advances on available, computationally intensive Monte Carlo methods. We study here an advanced version of familiar Markov Chain Monte Carlo (MCMC) algorithms that sample from target distributions defined as change of measures from Gaussian laws on general Hilbert spaces. Such a model structure arises in several contexts: we focus here at the important class of statistical models driven by diffusion paths whence the Wiener process constitutes the reference Gaussian law. Particular emphasis is given on advanced Hybrid Monte-Carlo (HMC) which makes large, derivative-driven steps in the state space (in contrast with local-move Random-walk-type algorithms) with analytical and experimental results. We illustrate it's computational advantages in various diffusion processes and observation regimes; examples include stochastic volatility and latent survival models. In contrast with their standard MCMC counterparts, the advanced versions have mesh-free mixing times, as these will not deteriorate upon refinement of the approximation of the inherently infinite-dimensional diffusion paths by finite-dimensional ones used in practice when applying the algorithms on a computer.