Poisson Midpoint Method for Log Concave Sampling: Beyond the Strong Error Lower Bounds
Probability
2025-10-02 v4 Machine Learning
Statistics Theory
Statistics Theory
Abstract
We study the problem of sampling from strongly log-concave distributions over using the Poisson midpoint discretization (a variant of the randomized midpoint method) for overdamped/underdamped Langevin dynamics. We prove its convergence in the 2-Wasserstein distance (), achieving a cubic speedup in dependence on the target accuracy () over the Euler-Maruyama discretization, surpassing existing bounds for randomized midpoint methods. Notably, in the case of underdamped Langevin dynamics, we demonstrate the complexity of convergence is much smaller than the complexity lower bounds for convergence in strong error established in the literature.
Cite
@article{arxiv.2506.07614,
title = {Poisson Midpoint Method for Log Concave Sampling: Beyond the Strong Error Lower Bounds},
author = {Rishikesh Srinivasan and Dheeraj Nagaraj},
journal= {arXiv preprint arXiv:2506.07614},
year = {2025}
}