对抗性稳健学习与宽容

H. Ashtiani, Vinayak Pathak, Ruth Urner
{"title":"对抗性稳健学习与宽容","authors":"H. Ashtiani, Vinayak Pathak, Ruth Urner","doi":"10.48550/arXiv.2203.00849","DOIUrl":null,"url":null,"abstract":"We initiate the study of tolerant adversarial PAC-learning with respect to metric perturbation sets. In adversarial PAC-learning, an adversary is allowed to replace a test point $x$ with an arbitrary point in a closed ball of radius $r$ centered at $x$. In the tolerant version, the error of the learner is compared with the best achievable error with respect to a slightly larger perturbation radius $(1+\\gamma)r$. This simple tweak helps us bridge the gap between theory and practice and obtain the first PAC-type guarantees for algorithmic techniques that are popular in practice. Our first result concerns the widely-used ``perturb-and-smooth'' approach for adversarial learning. For perturbation sets with doubling dimension $d$, we show that a variant of these approaches PAC-learns any hypothesis class $\\mathcal{H}$ with VC-dimension $v$ in the $\\gamma$-tolerant adversarial setting with $O\\left(\\frac{v(1+1/\\gamma)^{O(d)}}{\\varepsilon}\\right)$ samples. This is in contrast to the traditional (non-tolerant) setting in which, as we show, the perturb-and-smooth approach can provably fail. Our second result shows that one can PAC-learn the same class using $\\widetilde{O}\\left(\\frac{d.v\\log(1+1/\\gamma)}{\\varepsilon^2}\\right)$ samples even in the agnostic setting. This result is based on a novel compression-based algorithm, and achieves a linear dependence on the doubling dimension as well as the VC-dimension. This is in contrast to the non-tolerant setting where there is no known sample complexity upper bound that depend polynomially on the VC-dimension.","PeriodicalId":267197,"journal":{"name":"International Conference on Algorithmic Learning Theory","volume":"107 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"Adversarially Robust Learning with Tolerance\",\"authors\":\"H. Ashtiani, Vinayak Pathak, Ruth Urner\",\"doi\":\"10.48550/arXiv.2203.00849\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We initiate the study of tolerant adversarial PAC-learning with respect to metric perturbation sets. In adversarial PAC-learning, an adversary is allowed to replace a test point $x$ with an arbitrary point in a closed ball of radius $r$ centered at $x$. In the tolerant version, the error of the learner is compared with the best achievable error with respect to a slightly larger perturbation radius $(1+\\\\gamma)r$. This simple tweak helps us bridge the gap between theory and practice and obtain the first PAC-type guarantees for algorithmic techniques that are popular in practice. Our first result concerns the widely-used ``perturb-and-smooth'' approach for adversarial learning. For perturbation sets with doubling dimension $d$, we show that a variant of these approaches PAC-learns any hypothesis class $\\\\mathcal{H}$ with VC-dimension $v$ in the $\\\\gamma$-tolerant adversarial setting with $O\\\\left(\\\\frac{v(1+1/\\\\gamma)^{O(d)}}{\\\\varepsilon}\\\\right)$ samples. This is in contrast to the traditional (non-tolerant) setting in which, as we show, the perturb-and-smooth approach can provably fail. Our second result shows that one can PAC-learn the same class using $\\\\widetilde{O}\\\\left(\\\\frac{d.v\\\\log(1+1/\\\\gamma)}{\\\\varepsilon^2}\\\\right)$ samples even in the agnostic setting. This result is based on a novel compression-based algorithm, and achieves a linear dependence on the doubling dimension as well as the VC-dimension. This is in contrast to the non-tolerant setting where there is no known sample complexity upper bound that depend polynomially on the VC-dimension.\",\"PeriodicalId\":267197,\"journal\":{\"name\":\"International Conference on Algorithmic Learning Theory\",\"volume\":\"107 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-03-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Conference on Algorithmic Learning Theory\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2203.00849\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Conference on Algorithmic Learning Theory","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2203.00849","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

摘要

我们开始了关于度量摄动集的容忍对抗性pac学习的研究。在对抗性pac学习中,对手可以将测试点$x$替换为以$x$为中心的半径$r$的封闭球中的任意点。在容忍版本中,将学习器的误差与相对于稍大的扰动半径$(1+\gamma)r$的最佳可实现误差进行比较。这个简单的调整帮助我们弥合了理论和实践之间的差距,并为在实践中流行的算法技术获得了第一个pac类型的保证。我们的第一个结果涉及对抗性学习中广泛使用的“扰动-平滑”方法。对于具有双重维度$d$的扰动集,我们证明了这些方法的一种变体pac -学习在具有$O\left(\frac{v(1+1/\gamma)^{O(d)}}{\varepsilon}\right)$样本的$\gamma$容忍对抗设置中具有vc维$v$的任何假设类$\mathcal{H}$。这与传统的(非容忍的)设置形成对比,正如我们所展示的,在传统的设置中,扰动和平滑方法可能会失败。我们的第二个结果表明,即使在不可知论设置中,也可以使用$\widetilde{O}\left(\frac{d.v\log(1+1/\gamma)}{\varepsilon^2}\right)$样本来pac学习相同的类。该结果基于一种新颖的基于压缩的算法,实现了对加倍维和vc维的线性依赖。这与非容忍设置相反,其中没有已知的样本复杂性上界,多项式地依赖于vc维。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Adversarially Robust Learning with Tolerance
We initiate the study of tolerant adversarial PAC-learning with respect to metric perturbation sets. In adversarial PAC-learning, an adversary is allowed to replace a test point $x$ with an arbitrary point in a closed ball of radius $r$ centered at $x$. In the tolerant version, the error of the learner is compared with the best achievable error with respect to a slightly larger perturbation radius $(1+\gamma)r$. This simple tweak helps us bridge the gap between theory and practice and obtain the first PAC-type guarantees for algorithmic techniques that are popular in practice. Our first result concerns the widely-used ``perturb-and-smooth'' approach for adversarial learning. For perturbation sets with doubling dimension $d$, we show that a variant of these approaches PAC-learns any hypothesis class $\mathcal{H}$ with VC-dimension $v$ in the $\gamma$-tolerant adversarial setting with $O\left(\frac{v(1+1/\gamma)^{O(d)}}{\varepsilon}\right)$ samples. This is in contrast to the traditional (non-tolerant) setting in which, as we show, the perturb-and-smooth approach can provably fail. Our second result shows that one can PAC-learn the same class using $\widetilde{O}\left(\frac{d.v\log(1+1/\gamma)}{\varepsilon^2}\right)$ samples even in the agnostic setting. This result is based on a novel compression-based algorithm, and achieves a linear dependence on the doubling dimension as well as the VC-dimension. This is in contrast to the non-tolerant setting where there is no known sample complexity upper bound that depend polynomially on the VC-dimension.
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:604180095
Book学术官方微信