Computer Science – Computational Complexity
Scientific paper
2009-02-21
Computer Science
Computational Complexity
Scientific paper
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).
Diakonikolas Ilias
Gopalan Parikshit
Jaiswal Ragesh
Servedio Rocco
Viola Emanuele
No associations
LandOfFree
Bounded Independence Fools Halfspaces does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Bounded Independence Fools Halfspaces, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Bounded Independence Fools Halfspaces will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-99037