Ilias Diakonikolas, R. Servedio, Li-Yang Tan, Andrew Wan
{"title":"A Regularity Lemma, and Low-Weight Approximators, for Low-Degree Polynomial Threshold Functions","authors":"Ilias Diakonikolas, R. Servedio, Li-Yang Tan, Andrew Wan","doi":"10.4086/toc.2014.v010a002","DOIUrl":null,"url":null,"abstract":"We give a \"regularity lemma\" for degree-d polynomial threshold functions (PTFs) over the Boolean cube {−1,1}^n. Roughly speaking, this result shows that every degree-d PTF can be decomposed into a constant number of subfunctions such that almost all of the subfunctions are close to being regular PTFs. Here a \"regular\" PTF is a PTF sign(p(x)) where the influence of each variable on the polynomial p(x) is a small fraction of the total influence of p. As an application of this regularity lemma, we prove that for any constants d >= 1, eps > 0, every degree-d PTF over n variables can be approximated to accuracy eps by a constant degree PTF that has integer weights of total magnitude O(n^d). This weight bound is shown to be optimal up to logarithmic factors.","PeriodicalId":328781,"journal":{"name":"2010 IEEE 25th Annual Conference on Computational Complexity","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"47","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 IEEE 25th Annual Conference on Computational Complexity","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4086/toc.2014.v010a002","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 47
Abstract
We give a "regularity lemma" for degree-d polynomial threshold functions (PTFs) over the Boolean cube {−1,1}^n. Roughly speaking, this result shows that every degree-d PTF can be decomposed into a constant number of subfunctions such that almost all of the subfunctions are close to being regular PTFs. Here a "regular" PTF is a PTF sign(p(x)) where the influence of each variable on the polynomial p(x) is a small fraction of the total influence of p. As an application of this regularity lemma, we prove that for any constants d >= 1, eps > 0, every degree-d PTF over n variables can be approximated to accuracy eps by a constant degree PTF that has integer weights of total magnitude O(n^d). This weight bound is shown to be optimal up to logarithmic factors.