Time-Inhomogeneous Preconditioned Langevin Dynamics

TL;DR

The paper introduces TIPreL, a novel time- and position-dependent preconditioned Langevin dynamics method that effectively addresses both global mode coverage and local mode exploration challenges in sampling.

Contribution

It proposes a new preconditioning framework with convergence guarantees under time- and space-dependent coefficients, extending prior theoretical results.

Findings

TIPreL outperforms existing schemes in ill-posed 2D examples.

TIPreL demonstrates efficiency in Bayesian logistic regression tasks.

Theoretical convergence is established under broader conditions.

Abstract

Langevin sampling from distributions of the form $p(x) \propto \exp(-\Psi(x))$ faces two major challenges: (global) mode coverage and (local) mode exploration. The first challenge is particularly relevant for multi-modal distributions with disjoint modes, whereas the second arises when the potential $\Psi$ exhibits diverse and ill-conditioned local mode geometry. To address these challenges, a common approach is to precondition Langevin dynamics with problem-specific information, such as the sample covariance or the local curvature of $\Psi$. However, existing preconditioner choices inherently involve a trade-off between global mode coverage and local mode exploration, and no prior method resolves both simultaneously. To overcome this limitation, we propose the TIPreL, which introduces a time- and position-dependent preconditioner. This design effectively addresses both challenges mentioned above within a single framework. We establish convergence of the resulting dynamics in the Wasserstein-2 distance both in continuous time and for a tamed Euler discretization. In particular, our analysis extends the existing state of the art by proving convergence under time- and space-dependent diffusion coefficients, and only locally Lipschitz drifts, which has not been covered by prior work. Finally, we experimentally compare TIPreL with competing preconditioning schemes on a two-dimensional, severely ill-posed example and on a Bayesian logistic regression task in higher dimensions, confirming the efficiency of the proposed method.