file.pdf (417.92 kB)
Fooling Functions of Halfspaces under Product Distributions
journal contributionposted on 1975-01-01, 00:00 authored by Parikshit Gopalan, Ryan O'Donnell, Yi Wu, David Zuckerman
We construct pseudorandom generators that fool functions of halfspaces (threshold functions) under a very broad class of product distributions. This class includes not only familiar cases such as the uniform distribution on the discrete cube, the uniform distribution on the solid cube, and the multivariate Gaussian distribution, but also includes any product of discrete distributions with probabilities bounded away from 0. Our first main result shows that a recent pseudorandom generator construction of Meka and Zuckerman , when suitably modified, can fool arbitrary functions of d halfspaces under product distributions where each coordinate has bounded fourth moment. To e-fool any size-s, depth-d decision tree of halfspaces, our pseudorandom generator uses seed length O((dlog(ds/∈) + log n)·log(ds/∈)). For monotone functions of d halfspaces, the seed length can be improved to O((dlog(d/∈) + logn) · log(d/∈)). We get better bounds for larger e; for example, to l/polylog(n)-fool all monotone functions of (log n)l log log n halfspaces, our generator requires a seed of length just O(logn). Our second main result generalizes the work of Diakonikolas et al. to show that bounded independence suffices to fool functions of halfspaces under product distributions. Assuming each coordinate satisfies a certain stronger moment condition, we show that any function computable by a size-s, depth-d decision tree of halfspaces is e-fooled by Õ(d4s2/∈2)-wise independence. Our technical contributions include: a new multidimensional version of the classical Berry-Esseen theorem; a derandomization thereof; a generalization of Servedio's regularity lemma for halfspaces which works under any product distribution with bounded fourth moments; an extension of this regularity lemma to functions of many halfspaces; and, new analysis of the sandwiching polynomials technique of Bazzi for arbitrary pro- - duct distributions.