单调类学习的超多项式下界

N. Bshouty
{"title":"单调类学习的超多项式下界","authors":"N. Bshouty","doi":"10.48550/arXiv.2301.08486","DOIUrl":null,"url":null,"abstract":"Koch, Strassle, and Tan [SODA 2023], show that, under the randomized exponential time hypothesis, there is no distribution-free PAC-learning algorithm that runs in time $n^{\\tilde O(\\log\\log s)}$ for the classes of $n$-variable size-$s$ DNF, size-$s$ Decision Tree, and $\\log s$-Junta by DNF (that returns a DNF hypothesis). Assuming a natural conjecture on the hardness of set cover, they give the lower bound $n^{\\Omega(\\log s)}$. This matches the best known upper bound for $n$-variable size-$s$ Decision Tree, and $\\log s$-Junta. In this paper, we give the same lower bounds for PAC-learning of $n$-variable size-$s$ Monotone DNF, size-$s$ Monotone Decision Tree, and Monotone $\\log s$-Junta by~DNF. This solves the open problem proposed by Koch, Strassle, and Tan and subsumes the above results. The lower bound holds, even if the learner knows the distribution, can draw a sample according to the distribution in polynomial time, and can compute the target function on all the points of the support of the distribution in polynomial time.","PeriodicalId":11639,"journal":{"name":"Electron. Colloquium Comput. Complex.","volume":"46 1","pages":"34:1-34:20"},"PeriodicalIF":0.0000,"publicationDate":"2023-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Superpolynomial Lower Bounds for Learning Monotone Classes\",\"authors\":\"N. Bshouty\",\"doi\":\"10.48550/arXiv.2301.08486\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Koch, Strassle, and Tan [SODA 2023], show that, under the randomized exponential time hypothesis, there is no distribution-free PAC-learning algorithm that runs in time $n^{\\\\tilde O(\\\\log\\\\log s)}$ for the classes of $n$-variable size-$s$ DNF, size-$s$ Decision Tree, and $\\\\log s$-Junta by DNF (that returns a DNF hypothesis). Assuming a natural conjecture on the hardness of set cover, they give the lower bound $n^{\\\\Omega(\\\\log s)}$. This matches the best known upper bound for $n$-variable size-$s$ Decision Tree, and $\\\\log s$-Junta. In this paper, we give the same lower bounds for PAC-learning of $n$-variable size-$s$ Monotone DNF, size-$s$ Monotone Decision Tree, and Monotone $\\\\log s$-Junta by~DNF. This solves the open problem proposed by Koch, Strassle, and Tan and subsumes the above results. The lower bound holds, even if the learner knows the distribution, can draw a sample according to the distribution in polynomial time, and can compute the target function on all the points of the support of the distribution in polynomial time.\",\"PeriodicalId\":11639,\"journal\":{\"name\":\"Electron. Colloquium Comput. Complex.\",\"volume\":\"46 1\",\"pages\":\"34:1-34:20\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-01-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Electron. Colloquium Comput. Complex.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2301.08486\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Electron. Colloquium Comput. Complex.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2301.08486","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

Koch, Strassle和Tan [SODA 2023]表明,在随机指数时间假设下,对于$n$ -可变大小- $s$ DNF,大小- $s$决策树和$\log s$ - junta的DNF类(返回DNF假设),没有无分布的pac学习算法可以在时间$n^{\tilde O(\log\log s)}$上运行。假设对集盖的硬度有一个自然的猜想,他们给出了下界$n^{\Omega(\log s)}$。这与最著名的$n$ -可变大小- $s$决策树和$\log s$ -军政府的上界相匹配。在本文中,我们给出了$n$ -可变大小- $s$单调DNF、大小- $s$单调决策树和单调$\log s$ - junta的相同下界。这解决了Koch, Strassle和Tan提出的开放性问题,并将上述结果纳入其中。下界成立,即使学习者知道分布,也可以在多项式时间内根据分布绘制样本,并在多项式时间内计算出支持分布的所有点上的目标函数。
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
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Superpolynomial Lower Bounds for Learning Monotone Classes
Koch, Strassle, and Tan [SODA 2023], show that, under the randomized exponential time hypothesis, there is no distribution-free PAC-learning algorithm that runs in time $n^{\tilde O(\log\log s)}$ for the classes of $n$-variable size-$s$ DNF, size-$s$ Decision Tree, and $\log s$-Junta by DNF (that returns a DNF hypothesis). Assuming a natural conjecture on the hardness of set cover, they give the lower bound $n^{\Omega(\log s)}$. This matches the best known upper bound for $n$-variable size-$s$ Decision Tree, and $\log s$-Junta. In this paper, we give the same lower bounds for PAC-learning of $n$-variable size-$s$ Monotone DNF, size-$s$ Monotone Decision Tree, and Monotone $\log s$-Junta by~DNF. This solves the open problem proposed by Koch, Strassle, and Tan and subsumes the above results. The lower bound holds, even if the learner knows the distribution, can draw a sample according to the distribution in polynomial time, and can compute the target function on all the points of the support of the distribution in polynomial time.
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
期刊最新文献
Dependency schemes in CDCL-based QBF solving: a proof-theoretic study On blocky ranks of matrices Fractional Linear Matroid Matching is in quasi-NC Aaronson-Ambainis Conjecture Is True For Random Restrictions Optimal Pseudorandom Generators for Low-Degree Polynomials Over Moderately Large Fields
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1