无限制的学习过程

S. Mendelson
{"title":"无限制的学习过程","authors":"S. Mendelson","doi":"10.1145/3361699","DOIUrl":null,"url":null,"abstract":"We study learning problems involving arbitrary classes of functions F, underlying measures μ, and targets Y. Because proper learning procedures, i.e., procedures that are only allowed to select functions in F, tend to perform poorly unless the problem satisfies some additional structural property (e.g., that F is convex), we consider unrestricted learning procedures that are free to choose functions outside the given class. We present a new unrestricted procedure whose sample complexity is almost the best that one can hope for and holds for (almost) any problem, including heavy-tailed situations. Moreover, the sample complexity coincides with what one could expect if F were convex, even when F is not. And if F is convex, then the unrestricted procedure turns out to be proper.","PeriodicalId":17199,"journal":{"name":"Journal of the ACM (JACM)","volume":"134 1","pages":"1 - 42"},"PeriodicalIF":0.0000,"publicationDate":"2019-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":"{\"title\":\"An Unrestricted Learning Procedure\",\"authors\":\"S. Mendelson\",\"doi\":\"10.1145/3361699\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We study learning problems involving arbitrary classes of functions F, underlying measures μ, and targets Y. Because proper learning procedures, i.e., procedures that are only allowed to select functions in F, tend to perform poorly unless the problem satisfies some additional structural property (e.g., that F is convex), we consider unrestricted learning procedures that are free to choose functions outside the given class. We present a new unrestricted procedure whose sample complexity is almost the best that one can hope for and holds for (almost) any problem, including heavy-tailed situations. Moreover, the sample complexity coincides with what one could expect if F were convex, even when F is not. And if F is convex, then the unrestricted procedure turns out to be proper.\",\"PeriodicalId\":17199,\"journal\":{\"name\":\"Journal of the ACM (JACM)\",\"volume\":\"134 1\",\"pages\":\"1 - 42\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-11-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"12\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of the ACM (JACM)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3361699\",\"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 the ACM (JACM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3361699","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 12

摘要

我们研究涉及函数F、底层测度μ和目标y的任意类的学习问题。因为适当的学习过程,即只允许在F中选择函数的过程,往往表现不佳,除非问题满足一些额外的结构性质(例如,F是凸的),我们考虑可以自由选择给定类之外的函数的无限制学习过程。我们提出了一个新的不受限制的过程,它的样本复杂度几乎是人们所能期望的最好的,并且适用于(几乎)任何问题,包括重尾情况。此外,即使F不是凸的,样本复杂度也与F是凸的情况下的期望一致。如果F是凸的,那么无限制的过程就是合适的。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
An Unrestricted Learning Procedure
We study learning problems involving arbitrary classes of functions F, underlying measures μ, and targets Y. Because proper learning procedures, i.e., procedures that are only allowed to select functions in F, tend to perform poorly unless the problem satisfies some additional structural property (e.g., that F is convex), we consider unrestricted learning procedures that are free to choose functions outside the given class. We present a new unrestricted procedure whose sample complexity is almost the best that one can hope for and holds for (almost) any problem, including heavy-tailed situations. Moreover, the sample complexity coincides with what one could expect if F were convex, even when F is not. And if F is convex, then the unrestricted procedure turns out to be proper.
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