Weak Convergence of Approximate reflection coupling and its Application to Non-convex Optimization

MaRDI QIDQ6400032zbMATH OpenFDO

Authors Keisuke Suzuki

Publication date 24 May 2022

Mathematics Subject Classification ID

Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20)

Abstract: In this paper, we propose a weak approximation of the reflection coupling (RC) for stochastic differential equations (SDEs), and prove it converges weakly to the desired coupling. In contrast to the RC, the proposed approximate reflection coupling (ARC) need not take the hitting time of processes to the diagonal set into consideration and can be defined as the solution of some SDEs on the whole time interval. Therefore, ARC can work effectively against SDEs with different drift terms. As an application of ARC, an evaluation on the effectiveness of the stochastic gradient descent in a non-convex setting is also described. For the sample size $n$, the step size $eta$, and the batch size $B$, we derive uniform evaluations on the time with orders $n^{-1}$, $et{a}^{1/2}$, and $sqrt(n-B)/B(n-1)$, respectively.

This page was built for publication: Weak Convergence of Approximate reflection coupling and its Application to Non-convex Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6400032)