Subsampled Stochastic Variance-Reduced Gradient Langevin Dynamics

Difan Zou, Pan Xu, Quanquan Gu
2018 Conference on Uncertainty in Artificial Intelligence  
Stochastic variance-reduced gradient Langevin dynamics (SVRG-LD) was recently proposed to improve the performance of stochastic gradient Langevin dynamics (SGLD) by reducing the variance of the stochastic gradient. In this paper, we propose a variant of SVRG-LD, namely SVRG-LD + , which replaces the full gradient in each epoch with a subsampled one. We provide a nonasymptotic analysis of the convergence of SVRG-LD + in 2-Wasserstein distance, and show that SVRG-LD + enjoys a lower gradient
more » ... exity 1 than SVRG-LD, when the sample size is large or the target accuracy requirement is moderate. Our analysis directly implies a sharper convergence rate for SVRG-LD, which improves the existing convergence rate by a factor of κ 1/6 n 1/6 , where κ is the condition number of the log-density function and n is the sample size. Experiments on both synthetic and real-world datasets validate our theoretical results. * Equal contribution 1 Gradient complexity is defined as the required number of stochastic gradient evaluations to reach a target accuracy.
dblp:conf/uai/ZouXG18 fatcat:4ppgjbzrs5dfnaef3ibm5lhawe