用简单函数的线性组合表示布尔函数的限制:阈值,relu和低次多项式

Richard Ryan Williams
{"title":"用简单函数的线性组合表示布尔函数的限制:阈值,relu和低次多项式","authors":"Richard Ryan Williams","doi":"10.4230/LIPIcs.CCC.2018.6","DOIUrl":null,"url":null,"abstract":"We consider the problem of representing Boolean functions exactly by \"sparse\" linear combinations (over $\\mathbb{R}$) of functions from some \"simple\" class ${\\cal C}$. In particular, given ${\\cal C}$ we are interested in finding low-complexity functions lacking sparse representations. When ${\\cal C}$ is the set of PARITY functions or the set of conjunctions, this sort of problem has a well-understood answer, the problem becomes interesting when ${\\cal C}$ is \"overcomplete\" and the set of functions is not linearly independent. We focus on the cases where ${\\cal C}$ is the set of linear threshold functions, the set of rectified linear units (ReLUs), and the set of low-degree polynomials over a finite field, all of which are well-studied in different contexts. \nWe provide generic tools for proving lower bounds on representations of this kind. Applying these, we give several new lower bounds for \"semi-explicit\" Boolean functions. For example, we show there are functions in nondeterministic quasi-polynomial time that require super-polynomial size: \n$\\bullet$ Depth-two neural networks with sign activation function, a special case of depth-two threshold circuit lower bounds. \n$\\bullet$ Depth-two neural networks with ReLU activation function. \n$\\bullet$ $\\mathbb{R}$-linear combinations of $O(1)$-degree $\\mathbb{F}_p$-polynomials, for every prime $p$ (related to problems regarding Higher-Order \"Uncertainty Principles\"). We also obtain a function in $E^{NP}$ requiring $2^{\\Omega(n)}$ linear combinations. \n$\\bullet$ $\\mathbb{R}$-linear combinations of $ACC \\circ THR$ circuits of polynomial size (further generalizing the recent lower bounds of Murray and the author). \n(The above is a shortened abstract. For the full abstract, see the paper.)","PeriodicalId":246506,"journal":{"name":"Cybersecurity and Cyberforensics Conference","volume":"30 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"23","resultStr":"{\"title\":\"Limits on representing Boolean functions by linear combinations of simple functions: thresholds, ReLUs, and low-degree polynomials\",\"authors\":\"Richard Ryan Williams\",\"doi\":\"10.4230/LIPIcs.CCC.2018.6\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We consider the problem of representing Boolean functions exactly by \\\"sparse\\\" linear combinations (over $\\\\mathbb{R}$) of functions from some \\\"simple\\\" class ${\\\\cal C}$. In particular, given ${\\\\cal C}$ we are interested in finding low-complexity functions lacking sparse representations. When ${\\\\cal C}$ is the set of PARITY functions or the set of conjunctions, this sort of problem has a well-understood answer, the problem becomes interesting when ${\\\\cal C}$ is \\\"overcomplete\\\" and the set of functions is not linearly independent. We focus on the cases where ${\\\\cal C}$ is the set of linear threshold functions, the set of rectified linear units (ReLUs), and the set of low-degree polynomials over a finite field, all of which are well-studied in different contexts. \\nWe provide generic tools for proving lower bounds on representations of this kind. Applying these, we give several new lower bounds for \\\"semi-explicit\\\" Boolean functions. For example, we show there are functions in nondeterministic quasi-polynomial time that require super-polynomial size: \\n$\\\\bullet$ Depth-two neural networks with sign activation function, a special case of depth-two threshold circuit lower bounds. \\n$\\\\bullet$ Depth-two neural networks with ReLU activation function. \\n$\\\\bullet$ $\\\\mathbb{R}$-linear combinations of $O(1)$-degree $\\\\mathbb{F}_p$-polynomials, for every prime $p$ (related to problems regarding Higher-Order \\\"Uncertainty Principles\\\"). We also obtain a function in $E^{NP}$ requiring $2^{\\\\Omega(n)}$ linear combinations. \\n$\\\\bullet$ $\\\\mathbb{R}$-linear combinations of $ACC \\\\circ THR$ circuits of polynomial size (further generalizing the recent lower bounds of Murray and the author). \\n(The above is a shortened abstract. For the full abstract, see the paper.)\",\"PeriodicalId\":246506,\"journal\":{\"name\":\"Cybersecurity and Cyberforensics Conference\",\"volume\":\"30 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-02-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"23\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Cybersecurity and Cyberforensics Conference\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.4230/LIPIcs.CCC.2018.6\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cybersecurity and Cyberforensics Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4230/LIPIcs.CCC.2018.6","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 23

摘要

我们考虑用来自某个“简单”类${\cal}$的函数的“稀疏”线性组合(在$\mathbb{R}$上)精确地表示布尔函数的问题。特别地,给定${\cal C}$,我们感兴趣的是寻找缺乏稀疏表示的低复杂度函数。当${\cal C}$是奇偶函数集或连词集时,这类问题有一个很好的答案,当${\cal C}$是“过完备”且函数集不是线性无关时,问题就变得有趣了。我们关注的是${\cal}$是线性阈值函数集、整流线性单元集(relu)和有限域上的低次多项式集的情况,所有这些都在不同的背景下得到了很好的研究。我们提供了证明这类表示的下界的一般工具。应用这些,我们给出了“半显式”布尔函数的几个新的下界。例如,我们证明了在不确定的拟多项式时间内存在需要超多项式大小的函数:具有符号激活函数的深度二神经网络,深度二阈值电路下界的特殊情况。deep -two neural networks with ReLU activation function。$\bullet$ $\mathbb{R}$- $O(1)$-degree $\mathbb{F}_p$-多项式的线性组合,对于每个素数$p$(与高阶“不确定性原理”相关的问题)。我们也得到了$E^{NP}$中需要$2^{\Omega(n)}$线性组合的函数。$\bullet$ $\mathbb{R}$-多项式大小的$ACC \circ THR$电路的线性组合(进一步推广了Murray和作者最近的下界)。以上是一个简短的摘要。完整的摘要请参见论文。)
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Limits on representing Boolean functions by linear combinations of simple functions: thresholds, ReLUs, and low-degree polynomials
We consider the problem of representing Boolean functions exactly by "sparse" linear combinations (over $\mathbb{R}$) of functions from some "simple" class ${\cal C}$. In particular, given ${\cal C}$ we are interested in finding low-complexity functions lacking sparse representations. When ${\cal C}$ is the set of PARITY functions or the set of conjunctions, this sort of problem has a well-understood answer, the problem becomes interesting when ${\cal C}$ is "overcomplete" and the set of functions is not linearly independent. We focus on the cases where ${\cal C}$ is the set of linear threshold functions, the set of rectified linear units (ReLUs), and the set of low-degree polynomials over a finite field, all of which are well-studied in different contexts. We provide generic tools for proving lower bounds on representations of this kind. Applying these, we give several new lower bounds for "semi-explicit" Boolean functions. For example, we show there are functions in nondeterministic quasi-polynomial time that require super-polynomial size: $\bullet$ Depth-two neural networks with sign activation function, a special case of depth-two threshold circuit lower bounds. $\bullet$ Depth-two neural networks with ReLU activation function. $\bullet$ $\mathbb{R}$-linear combinations of $O(1)$-degree $\mathbb{F}_p$-polynomials, for every prime $p$ (related to problems regarding Higher-Order "Uncertainty Principles"). We also obtain a function in $E^{NP}$ requiring $2^{\Omega(n)}$ linear combinations. $\bullet$ $\mathbb{R}$-linear combinations of $ACC \circ THR$ circuits of polynomial size (further generalizing the recent lower bounds of Murray and the author). (The above is a shortened abstract. For the full abstract, see the paper.)
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