🤖 AI Summary
Existing theoretical analyses of kinetic Langevin Monte Carlo (KLMC) under stochastic exponential Euler discretization are restricted to the underdamped regime and break down in the overdamped limit, suggesting degradation of the exponential integrator. Method: We propose an improved synchronous Wasserstein coupling framework that integrates kinetic Langevin dynamics modeling, exponential discretization, and asymptotic bias estimation. Contribution/Results: We establish, for the first time, rigorous stability and effectiveness guarantees for this integrator across the entire parameter spectrum—from underdamped to overdamped regimes. Our analysis yields Wasserstein contraction bounds and asymptotic bias upper bounds under milder conditions than prior work. The results substantially broaden the admissible parameter range for KLMC, confirming its robustness and sampling efficiency across a wide spectrum of damping coefficients.
📝 Abstract
Simulating the kinetic Langevin dynamics is a popular approach for sampling from distributions, where only their unnormalized densities are available. Various discretizations of the kinetic Langevin dynamics have been considered, where the resulting algorithm is collectively referred to as the kinetic Langevin Monte Carlo (KLMC) or underdamped Langevin Monte Carlo. Specifically, the stochastic exponential Euler discretization, or exponential integrator for short, has previously been studied under strongly log-concave and log-Lipschitz smooth potentials via the synchronous Wasserstein coupling strategy. Existing analyses, however, impose restrictions on the parameters that do not explain the behavior of KLMC under various choices of parameters. In particular, all known results fail to hold in the overdamped regime, suggesting that the exponential integrator degenerates in the overdamped limit. In this work, we revisit the synchronous Wasserstein coupling analysis of KLMC with the exponential integrator. Our refined analysis results in Wasserstein contractions and bounds on the asymptotic bias that hold under weaker restrictions on the parameters, which assert that the exponential integrator is capable of stably simulating the kinetic Langevin dynamics in the overdamped regime, as long as proper time acceleration is applied.