超越单调的近端梯度方法

A. Marchi
{"title":"超越单调的近端梯度方法","authors":"A. Marchi","doi":"10.46298/jnsao-2023-10290","DOIUrl":null,"url":null,"abstract":"We address composite optimization problems, which consist in minimizing the\nsum of a smooth and a merely lower semicontinuous function, without any\nconvexity assumptions. Numerical solutions of these problems can be obtained by\nproximal gradient methods, which often rely on a line search procedure as\nglobalization mechanism. We consider an adaptive nonmonotone proximal gradient\nscheme based on an averaged merit function and establish asymptotic convergence\nguarantees under weak assumptions, delivering results on par with the monotone\nstrategy. Global worst-case rates for the iterates and a stationarity measure\nare also derived. Finally, a numerical example indicates the potential of\nnonmonotonicity and spectral approximations.","PeriodicalId":250939,"journal":{"name":"Journal of Nonsmooth Analysis and Optimization","volume":"259 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Proximal gradient methods beyond monotony\",\"authors\":\"A. Marchi\",\"doi\":\"10.46298/jnsao-2023-10290\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We address composite optimization problems, which consist in minimizing the\\nsum of a smooth and a merely lower semicontinuous function, without any\\nconvexity assumptions. Numerical solutions of these problems can be obtained by\\nproximal gradient methods, which often rely on a line search procedure as\\nglobalization mechanism. We consider an adaptive nonmonotone proximal gradient\\nscheme based on an averaged merit function and establish asymptotic convergence\\nguarantees under weak assumptions, delivering results on par with the monotone\\nstrategy. Global worst-case rates for the iterates and a stationarity measure\\nare also derived. Finally, a numerical example indicates the potential of\\nnonmonotonicity and spectral approximations.\",\"PeriodicalId\":250939,\"journal\":{\"name\":\"Journal of Nonsmooth Analysis and Optimization\",\"volume\":\"259 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Nonsmooth Analysis and Optimization\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.46298/jnsao-2023-10290\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Nonsmooth Analysis and Optimization","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.46298/jnsao-2023-10290","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

摘要

我们解决复合优化问题,它包括最小化光滑和下半连续函数的和,没有任何凸性假设。这些问题的数值解可以通过近端梯度法得到,这种方法通常依赖于线搜索过程作为全球化机制。我们考虑了一种基于平均价值函数的自适应非单调近端梯度方案,并在弱假设下建立了渐近收敛保证,得到了与单调策略相当的结果。还推导了迭代的全局最坏情况率和平稳性度量。最后,通过数值算例说明了非单调性和谱近似的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Proximal gradient methods beyond monotony
We address composite optimization problems, which consist in minimizing the sum of a smooth and a merely lower semicontinuous function, without any convexity assumptions. Numerical solutions of these problems can be obtained by proximal gradient methods, which often rely on a line search procedure as globalization mechanism. We consider an adaptive nonmonotone proximal gradient scheme based on an averaged merit function and establish asymptotic convergence guarantees under weak assumptions, delivering results on par with the monotone strategy. Global worst-case rates for the iterates and a stationarity measure are also derived. Finally, a numerical example indicates the potential of nonmonotonicity and spectral approximations.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信