Angan Mitra, K. Nguyen, T. Nguyen, D. Trystram, P. Youssef
{"title":"在线分散式Frank-Wolfe:从理论约束到智能建筑的应用","authors":"Angan Mitra, K. Nguyen, T. Nguyen, D. Trystram, P. Youssef","doi":"10.48550/arXiv.2208.00522","DOIUrl":null,"url":null,"abstract":"The design of decentralized learning algorithms is important in the fast-growing world in which data are distributed over participants with limited local computation resources and communication. In this direction, we propose an online algorithm minimizing non-convex loss functions aggregated from individual data/models distributed over a network. We provide the theoretical performance guarantee of our algorithm and demonstrate its utility on a real life smart building.","PeriodicalId":140428,"journal":{"name":"Global Internet of Things Summit","volume":"33 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Online Decentralized Frank-Wolfe: From theoretical bound to applications in smart-building\",\"authors\":\"Angan Mitra, K. Nguyen, T. Nguyen, D. Trystram, P. Youssef\",\"doi\":\"10.48550/arXiv.2208.00522\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The design of decentralized learning algorithms is important in the fast-growing world in which data are distributed over participants with limited local computation resources and communication. In this direction, we propose an online algorithm minimizing non-convex loss functions aggregated from individual data/models distributed over a network. We provide the theoretical performance guarantee of our algorithm and demonstrate its utility on a real life smart building.\",\"PeriodicalId\":140428,\"journal\":{\"name\":\"Global Internet of Things Summit\",\"volume\":\"33 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-07-31\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Global Internet of Things Summit\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2208.00522\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Global Internet of Things Summit","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2208.00522","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Online Decentralized Frank-Wolfe: From theoretical bound to applications in smart-building
The design of decentralized learning algorithms is important in the fast-growing world in which data are distributed over participants with limited local computation resources and communication. In this direction, we propose an online algorithm minimizing non-convex loss functions aggregated from individual data/models distributed over a network. We provide the theoretical performance guarantee of our algorithm and demonstrate its utility on a real life smart building.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
