Kinetic Interacting Particle Langevin Monte Carlo

TL;DR

This paper develops and analyzes Kinetic Interacting Particle Langevin Monte Carlo methods, providing new algorithms with accelerated convergence for statistical inference in latent variable models.

Contribution

It introduces a novel diffusion process and discretizations for efficient parameter estimation, with proven convergence rates and broad applicability.

Findings

Nonasymptotic convergence rates in Wasserstein-2 distance.

Accelerated convergence with improved dimension dependence.

Numerical experiments demonstrating effectiveness in various applications.

Abstract

This paper introduces and analyses interacting underdamped Langevin algorithms, termed Kinetic Interacting Particle Langevin Monte Carlo (KIPLMC) methods, for statistical inference in latent variable models. We propose a diffusion process that evolves jointly in the space of parameters and latent variables and show that the stationary distribution of this diffusion concentrates around the maximum marginal likelihood estimate of the parameters. We then provide two explicit discretisations of this diffusion as practical algorithms to estimate parameters of statistical models. For each algorithm, we obtain nonasymptotic rates of convergence in Wasserstein-2 distance for the case where the joint log-likelihood is strongly concave with respect to latent variables and parameters. We achieve accelerated convergence rates clearly demonstrating improvement in dimension dependence. To demonstrate the utility of the introduced methodology, we provide numerical experiments that illustrate the effectiveness of the proposed diffusion for statistical inference. Our setting covers a broad number of applications, including unsupervised learning, statistical inference, and inverse problems.