Saved in:
Bibliographic Details
Main Authors: Huang, Zhishen, Becker, Stephen
Format: Preprint
Published: 2021
Subjects:
Online Access:https://arxiv.org/abs/2102.06759
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913416544780288
author Huang, Zhishen
Becker, Stephen
author_facet Huang, Zhishen
Becker, Stephen
contents Stochastic gradient Langevin dynamics (SGLD) has gained the attention of optimization researchers due to its global optimization properties. This paper proves an improved convergence property to local minimizers of nonconvex objective functions using SGLD accelerated by variance reductions. Moreover, we prove an ergodicity property of the SGLD scheme, which gives insights on its potential to find global minimizers of nonconvex objectives.
format Preprint
id arxiv_https___arxiv_org_abs_2102_06759
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Stochastic Gradient Langevin Dynamics with Variance Reduction
Huang, Zhishen
Becker, Stephen
Machine Learning
Optimization and Control
Stochastic gradient Langevin dynamics (SGLD) has gained the attention of optimization researchers due to its global optimization properties. This paper proves an improved convergence property to local minimizers of nonconvex objective functions using SGLD accelerated by variance reductions. Moreover, we prove an ergodicity property of the SGLD scheme, which gives insights on its potential to find global minimizers of nonconvex objectives.
title Stochastic Gradient Langevin Dynamics with Variance Reduction
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2102.06759