典型文献
STOCHASTIC TRUST-REGION METHODS WITH TRUST-REGION RADIUS DEPENDING ON PROBABILISTIC MODELS
文献摘要：
We present a stochastic trust-region model-based framework in which its radius is related to the probabilistic models.Especially,we propose a specific algorithm termed STRME,in which the trust-region radius depends linearly on the gradient used to define the latest model.The complexity results of the STRME method in nonconvex,convex and strongly convex settings are presented,which match those of the existing algorithms based on probabilistic properties.In addition,several numerical experiments are carried out to reveal the benefits of the proposed methods compared to the existing stochastic trust-region methods and other relevant stochastic gradient methods.
文献关键词：
中图分类号：
作者姓名：
Xiaoyu Wang;Ya-xiang Yuan
作者机构：
Institute of Computational Mathematics and Scientific/Engineering Computing,Academy of Mathematics and Systems Science,Chinese Academy of Sciences,Beijing 100190,China;University of Chinese Academy of Sciences,Beijing 100049,China;State Key Laboratory of Scientific/Engineering Computing,Institute of Computational Mathematics and Scientific/Engineering Computing,Academy of Mathematics and Systems Science,Chinese Academy of Sciences,Beijing 100190,China
文献出处：
引用格式：
[1]Xiaoyu Wang;Ya-xiang Yuan-.STOCHASTIC TRUST-REGION METHODS WITH TRUST-REGION RADIUS DEPENDING ON PROBABILISTIC MODELS)[J].计算数学（英文版）,2022(02):294-334
A类：
STOCHASTIC,REGION,RADIUS,DEPENDING,PROBABILISTIC,MODELS,STRME
B类：
TRUST,METHODS,WITH,We,stochastic,trust,region,framework,which,radius,related,probabilistic,models,Especially,we,specific,termed,depends,linearly,gradient,used,define,latest,complexity,results,nonconvex,strongly,settings,presented,match,those,existing,algorithms,properties,In,addition,several,numerical,experiments,carried,out,reveal,benefits,proposed,methods,compared,other,relevant
AB值：
0.453508
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
