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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lu, Jianfeng, Ye, Xuda, Zhou, Zhennan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912691403096064
author Lu, Jianfeng
Ye, Xuda
Zhou, Zhennan
author_facet Lu, Jianfeng
Ye, Xuda
Zhou, Zhennan
contents 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 $h$, 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_04413
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mean square error analysis of stochastic gradient and variance-reduced sampling algorithms
Lu, Jianfeng
Ye, Xuda
Zhou, Zhennan
Numerical Analysis
65C30, 60H35, 62F15
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 $h$, 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.
title Mean square error analysis of stochastic gradient and variance-reduced sampling algorithms
topic Numerical Analysis
65C30, 60H35, 62F15
url https://arxiv.org/abs/2511.04413