双臂强盗问题的并行镜像下降算法

2016 Third International Conference on Mathematics and Computers in Sciences and in Industry (MCSI) Pub Date : 2016-08-01 DOI:10.1109/MCSI.2016.052

A. Kolnogorov, D. Shiyan

{"title":"双臂强盗问题的并行镜像下降算法","authors":"A. Kolnogorov, D. Shiyan","doi":"10.1109/MCSI.2016.052","DOIUrl":null,"url":null,"abstract":"We propose some modified versions of the mirror descent algorithm for the two-armed bandit problem which allow parallel processing of data. Using Monte-Carlo simulations, we estimate the minimax risk for this versions.","PeriodicalId":421998,"journal":{"name":"2016 Third International Conference on Mathematics and Computers in Sciences and in Industry (MCSI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Parallel Version of the Mirror Descent Algorithm for the Two-Armed Bandit Problem\",\"authors\":\"A. Kolnogorov, D. Shiyan\",\"doi\":\"10.1109/MCSI.2016.052\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose some modified versions of the mirror descent algorithm for the two-armed bandit problem which allow parallel processing of data. Using Monte-Carlo simulations, we estimate the minimax risk for this versions.\",\"PeriodicalId\":421998,\"journal\":{\"name\":\"2016 Third International Conference on Mathematics and Computers in Sciences and in Industry (MCSI)\",\"volume\":\"21 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 Third International Conference on Mathematics and Computers in Sciences and in Industry (MCSI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/MCSI.2016.052\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 Third International Conference on Mathematics and Computers in Sciences and in Industry (MCSI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MCSI.2016.052","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

摘要

针对双臂强盗问题，我们提出了一些改进版本的镜像下降算法，使数据能够并行处理。使用蒙特卡罗模拟，我们估计了这个版本的最小最大风险。

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

Parallel Version of the Mirror Descent Algorithm for the Two-Armed Bandit Problem

We propose some modified versions of the mirror descent algorithm for the two-armed bandit problem which allow parallel processing of data. Using Monte-Carlo simulations, we estimate the minimax risk for this versions.

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

2016 Third International Conference on Mathematics and Computers in Sciences and in Industry (MCSI)

自引率

0.00%

发文量