Stochastic proximal quasi-Newton methods for non-convex composite optimization

Author:

Wang Xiaoyu12,Wang Xiao2,Yuan Ya-xiang1

Affiliation:

1. LSEC, Institute of Computational Mathematics and Scientific/Engineering Computing, AMSS, Chinese Academy of Sciences, Beijing, People's Republic of China

2. School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, People's Republic of China

Funder

National Natural Science Foundation of China

Publisher

Informa UK Limited

Subject

Applied Mathematics,Control and Optimization,Software

Reference60 articles.

1. Z. Allen-Zhu, Natasha 2: Faster non-convex optimization than SGD, preprint (2017). Available at arXiv:1708.08694v2.

2. Z. Allen-Zhu, Natasha: Faster stochastic non-convex optimization via strongly non-convex parameter, preprint (2017). Available at arXiv:1702.00763.

3. Z. Allen-Zhu and E. Hazan, Variance reduction for faster non-convex optimization, International Conference on Machine Learning, New York, NY, 2016, pp. 699–707.

4. S. Becker and J. Fadili, A quasi-Newton proximal splitting method, Advances in Neural Information Processing Systems, Lake Tahoe, 2012, pp. 2618–2626.

Cited by 17 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. An Accelerated Stochastic Mirror Descent Method;Journal of the Operations Research Society of China;2023-08-29

2. A dual-based stochastic inexact algorithm for a class of stochastic nonsmooth convex composite problems;Computational Optimization and Applications;2023-07-16

3. An Overview of Stochastic Quasi-Newton Methods for Large-Scale Machine Learning;Journal of the Operations Research Society of China;2023-02-25

4. LSOS: Line-search second-order stochastic optimization methods for nonconvex finite sums;Mathematics of Computation;2022-12-02

5. Adaptive stochastic conjugate gradient for machine learning;Expert Systems with Applications;2022-11

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3