Sampling and Estimation on Manifolds using the Langevin Diffusion
Artikel i vetenskaplig tidskrift, 2025

Error bounds are derived for sampling and estimation using a discretization of an intrinsically defined Langevin diffusion with invariant measure d mu phi proportional to e-phi dvolg on a compact Riemannian manifold. Two estimators of linear functionals of mu phi based on the discretized Markov process are considered: a time-averaging estimator based on a single trajectory and an ensemble-averaging estimator based on multiple independent trajectories. Imposing no restrictions beyond a nominal level of smoothness on phi, first-order error bounds, in discretization step size, on the bias and variance/mean-square error of both estimators are derived. The order of error matches the optimal rate in Euclidean and flat spaces, and leads to a first-order bound on distance between the invariant measure mu phi and a stationary measure of the discretized Markov process. This order is preserved even upon using retractions when exponential maps are unavailable in closed form, thus enhancing practicality of the proposed algorithms. Generality of the proof techniques, which exploit links between two partial differential equations and the semigroup of operators corresponding to the Langevin diffusion, renders them amenable for the study of a more general class of sampling algorithms related to the Langevin diffusion. Conditions for extending analysis to the case of non-compact manifolds are discussed. Numerical illustrations with distributions, log-concave and otherwise, on the manifolds of positive and negative curvature elucidate on the derived bounds and demonstrate practical utility of the sampling algorithm.

Weak approximation

Intrinsic Riemannian geometry

Stochastic differential equations on manifolds

Computing ergodic limits

Monte Carlo technique

Författare

Karthik Bharath

University of Nottingham

Alexander Lewis

Georg-August-Universität Göttingen

Akash Sharma

Chalmers, Matematiska vetenskaper, Tillämpad matematik och statistik

Göteborgs universitet

Michael V. Tretyakov

University of Nottingham

Journal of Machine Learning Research

1532-4435 (ISSN) 1533-7928 (eISSN)

Vol. 26 71

Ämneskategorier (SSIF 2025)

Sannolikhetsteori och statistik

Mer information

Senast uppdaterat

2025-06-16