English

Mean square error analysis of stochastic gradient and variance-reduced sampling algorithms

Numerical Analysis 2025-11-07 v1 Numerical Analysis

Abstract

This paper considers mean square error (MSE) analysis for stochastic gradient sampling algorithms applied to underdamped Langevin dynamics under a global convexity assumption. A novel discrete Poisson equation framework is developed to bound the time-averaged sampling error. For the Stochastic Gradient UBU (SG-UBU) sampler, we derive an explicit MSE bound and establish that the numerical bias exhibits first-order convergence with respect to the step size hh, with the leading error coefficient proportional to the variance of the stochastic gradient. The analysis is further extended to variance-reduced algorithms for finite-sum potentials, specifically the SVRG-UBU and SAGA-UBU methods. For these algorithms, we identify a phase transition phenomenon whereby the convergence rate of the numerical bias shifts from first to second order as the step size decreases below a critical threshold. Theoretical findings are validated by numerical experiments. In addition, the analysis provides a practical empirical criterion for selecting between the mini-batch SG-UBU and SVRG-UBU samplers to achieve optimal computational efficiency.

Keywords

Cite

@article{arxiv.2511.04413,
  title  = {Mean square error analysis of stochastic gradient and variance-reduced sampling algorithms},
  author = {Jianfeng Lu and Xuda Ye and Zhennan Zhou},
  journal= {arXiv preprint arXiv:2511.04413},
  year   = {2025}
}
R2 v1 2026-07-01T07:24:38.590Z