Stochastic analysis of an adaptive cubic regularization method under inexact gradient evaluations and dynamic Hessian accuracy
Author:
Affiliation:
1. Dipartimento di Ingegneria Industriale, Università degli Studi, Firenze, Italy
2. Dipartimento di Matematica e Informatica “Ulisse Dini”, Università degli Studi, Firenze, Italy
Funder
INdAM
Publisher
Informa UK Limited
Subject
Applied Mathematics,Management Science and Operations Research,Control and Optimization
Link
https://www.tandfonline.com/doi/pdf/10.1080/02331934.2021.1892104
Reference29 articles.
1. Cubic regularization of Newton method and its global performance
2. Complexity bounds for second-order optimality in unconstrained optimization
3. On the Complexity of Steepest Descent, Newton's and Regularized Newton's Methods for Nonconvex Unconstrained Optimization Problems
4. An adaptive cubic regularization algorithm for nonconvex optimization with convex constraints and its function-evaluation complexity
5. 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. Stochastic Trust-Region and Direct-Search Methods: A Weak Tail Bound Condition and Reduced Sample Sizing;SIAM Journal on Optimization;2024-06-14
2. Subsampled cubic regularization method for finite-sum minimization;Optimization;2024-02-16
3. Stochastic Adaptive Regularization Method with Cubics: a High Probability Complexity Bound;2023 Winter Simulation Conference (WSC);2023-12-10
4. Inexact tensor methods and their application to stochastic convex optimization;Optimization Methods and Software;2023-11-17
5. The Impact of Noise on Evaluation Complexity: The Deterministic Trust-Region Case;Journal of Optimization Theory and Applications;2023-01-09
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