带班迪反馈的非平稳随机优化的自适应技术要点

IF 0.7 4区管理学 Q3 Engineering

Military Operations Research Pub Date : 2023-07-31 DOI:10.1287/opre.2022.0576

Yining Wang

{"title":"带班迪反馈的非平稳随机优化的自适应技术要点","authors":"Yining Wang","doi":"10.1287/opre.2022.0576","DOIUrl":null,"url":null,"abstract":"Optimal Nonstationary Optimization Without Knowing Function Changes Nonstationary stochastic optimization plays a vital role in a number of computer science and operations research applications. It is known how to design and analyze algorithms that optimize a sequence of strongly convex/concave and smooth functions with access to only one-point noisy function values with the underlying function sequence subject to maximum magnitude of function changes. In recent work from Wang titled “Technical Note: On Adaptivity in Nonstationary Stochastic Optimization with Bandit Feedback,” an optimization algorithm is designed and analyzed without assuming the magnitude of function changes is known in advance. Optimality of the designed algorithm is demonstrated.","PeriodicalId":49809,"journal":{"name":"Military Operations Research","volume":"24 1","pages":""},"PeriodicalIF":0.7000,"publicationDate":"2023-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Technical Note—On Adaptivity in Nonstationary Stochastic Optimization with Bandit Feedback\",\"authors\":\"Yining Wang\",\"doi\":\"10.1287/opre.2022.0576\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Optimal Nonstationary Optimization Without Knowing Function Changes Nonstationary stochastic optimization plays a vital role in a number of computer science and operations research applications. It is known how to design and analyze algorithms that optimize a sequence of strongly convex/concave and smooth functions with access to only one-point noisy function values with the underlying function sequence subject to maximum magnitude of function changes. In recent work from Wang titled “Technical Note: On Adaptivity in Nonstationary Stochastic Optimization with Bandit Feedback,” an optimization algorithm is designed and analyzed without assuming the magnitude of function changes is known in advance. Optimality of the designed algorithm is demonstrated.\",\"PeriodicalId\":49809,\"journal\":{\"name\":\"Military Operations Research\",\"volume\":\"24 1\",\"pages\":\"\"},\"PeriodicalIF\":0.7000,\"publicationDate\":\"2023-07-31\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Military Operations Research\",\"FirstCategoryId\":\"91\",\"ListUrlMain\":\"https://doi.org/10.1287/opre.2022.0576\",\"RegionNum\":4,\"RegionCategory\":\"管理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"Engineering\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Military Operations Research","FirstCategoryId":"91","ListUrlMain":"https://doi.org/10.1287/opre.2022.0576","RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Engineering","Score":null,"Total":0}

引用次数: 0

摘要

不知道函数变化的最优非平稳优化在许多计算机科学和运筹学应用中起着至关重要的作用。已知如何设计和分析算法来优化强凸/凹和光滑函数序列，这些函数只能访问一点噪声函数值，并且底层函数序列受函数变化的最大幅度影响。在Wang最近的一篇名为“技术说明:基于Bandit反馈的非平稳随机优化中的自适应性”的工作中，他设计并分析了一种优化算法，而不假设函数变化的幅度事先已知。验证了所设计算法的最优性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Technical Note—On Adaptivity in Nonstationary Stochastic Optimization with Bandit Feedback

Optimal Nonstationary Optimization Without Knowing Function Changes Nonstationary stochastic optimization plays a vital role in a number of computer science and operations research applications. It is known how to design and analyze algorithms that optimize a sequence of strongly convex/concave and smooth functions with access to only one-point noisy function values with the underlying function sequence subject to maximum magnitude of function changes. In recent work from Wang titled “Technical Note: On Adaptivity in Nonstationary Stochastic Optimization with Bandit Feedback,” an optimization algorithm is designed and analyzed without assuming the magnitude of function changes is known in advance. Optimality of the designed algorithm is demonstrated.

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

Military Operations Research 管理科学-运筹学与管理科学

CiteScore

1.00

自引率

0.00%

发文量

审稿时长

>12 weeks

期刊介绍： Military Operations Research is a peer-reviewed journal of high academic quality. The Journal publishes articles that describe operations research (OR) methodologies and theories used in key military and national security applications. Of particular interest are papers that present: Case studies showing innovative OR applications Apply OR to major policy issues Introduce interesting new problems areas Highlight education issues Document the history of military and national security OR.