Bounded Independence Fools Halfspaces
Ilias Diakonikolas, Parikshit Gopalan, Ragesh Jaiswal, Rocco Servedio,, Emanuele Viola

TL;DR
This paper proves that k-wise independent distributions can effectively fool halfspaces with small error, providing explicit pseudorandom generators with near-optimal seed length, by combining approximation theory and structural analysis.
Contribution
It establishes near-optimal bounds for fooling halfspaces with k-wise independence and constructs explicit pseudorandom generators with efficient seed length.
Findings
k-wise independence fools halfspaces with error psilon for k = O(\u03bclog^2(1/psilon)/psilon^2)
First explicit pseudorandom generators fooling halfspaces with seed length O(\u0003bclog n d7 bclog^2(1/psilon)/psilon^2)
Combines real approximation theory with structural results to achieve these bounds
Abstract
We show that any distribution on {-1,1}^n that is k-wise independent fools any halfspace h with error \eps for k = O(\log^2(1/\eps) /\eps^2). Up to logarithmic factors, our result matches a lower bound by Benjamini, Gurel-Gurevich, and Peled (2007) showing that k = \Omega(1/(\eps^2 \cdot \log(1/\eps))). Using standard constructions of k-wise independent distributions, we obtain the first explicit pseudorandom generators G: {-1,1}^s --> {-1,1}^n that fool halfspaces. Specifically, we fool halfspaces with error eps and seed length s = k \log n = O(\log n \cdot \log^2(1/\eps) /\eps^2). Our approach combines classical tools from real approximation theory with structural results on halfspaces by Servedio (Computational Complexity 2007).
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComplexity and Algorithms in Graphs · Machine Learning and Algorithms · Cryptography and Data Security
