A Newton-Based Method for Nonconvex Optimization with Fast Evasion of Saddle Points
Author:
Funder
Army Research Laboratory
Publisher
Society for Industrial & Applied Mathematics (SIAM)
Subject
Theoretical Computer Science,Software
Link
https://epubs.siam.org/doi/pdf/10.1137/17M1150116
Reference24 articles.
1. Neural networks and principal component analysis: Learning from examples without local minima
2. Accelerated Methods for NonConvex Optimization
3. Adaptive cubic regularisation methods for unconstrained optimization. Part I: motivation, convergence and numerical results
4. Adaptive cubic regularisation methods for unconstrained optimization. Part II: worst-case function- and derivative-evaluation complexity
Cited by 13 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. Stabler Neo-Hookean Simulation: Absolute Eigenvalue Filtering for Projected Newton;Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers '24;2024-07-13
2. A systematic approach for learning imbalanced data: enhancing zero-inflated models through boosting;Machine Learning;2024-07-08
3. Quantization avoids saddle points in distributed optimization;Proceedings of the National Academy of Sciences;2024-04-19
4. Boundary Conditions for Linear Exit Time Gradient Trajectories Around Saddle Points: Analysis and Algorithm;IEEE Transactions on Information Theory;2023-04
5. Exit Time Analysis for Approximations of Gradient Descent Trajectories Around Saddle Points;Information and Inference: A Journal of the IMA;2022-11-21
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