English

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 Rd\mathbb{R}^d 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 (W2W_2), achieving a cubic speedup in dependence on the target accuracy (ϵ\epsilon) 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 W2W_2 convergence is much smaller than the complexity lower bounds for convergence in L2L^2 strong error established in the literature.

Keywords

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}
}
R2 v1 2026-07-01T03:06:45.930Z