Cubic Regularization with Momentum for Nonconvex Optimization release_wgeoqk5ubra7repavy6mc66rne

by Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan

Released as a article .

2018  

Abstract

Momentum is a popular technique to accelerate the convergence in practical training, and its impact on convergence guarantee has been well-studied for first-order algorithms. However, such a successful acceleration technique has not yet been proposed for second-order algorithms in nonconvex optimization.In this paper, we apply the momentum scheme to cubic regularized (CR) Newton's method and explore the potential for acceleration. Our numerical experiments on various nonconvex optimization problems demonstrate that the momentum scheme can substantially facilitate the convergence of cubic regularization, and perform even better than the Nesterov's acceleration scheme for CR. Theoretically, we prove that CR under momentum achieves the best possible convergence rate to a second-order stationary point for nonconvex optimization. Moreover, we study the proposed algorithm for solving problems satisfying an error bound condition and establish a local quadratic convergence rate. Then, particularly for finite-sum problems, we show that the proposed algorithm can allow computational inexactness that reduces the overall sample complexity without degrading the convergence rate.
In text/plain format

Archived Files and Locations

application/pdf  839.5 kB
file_ayg2vnk4xrdbleta7eeeok75ua
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2018-10-09
Version   v1
Language   en ?
arXiv  1810.03763v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 858623a5-ca62-446f-adfc-88a960819381
API URL: JSON