Date of Original Version
Foundations of Computer Science, 2008. FOCS '08. IEEE 49th Annual IEEE Symposium on ,pp.541-550, 25-28 Oct. 2008
Abstract or Table of Contents
We study the learnability of sets in Rn under the Gaussian distribution, taking Gaussian surface area as the “complexity measure” of the sets being learned. Let CS denote the class of all (measurable) sets with surface area at most S. We first show that the class CS is learnable to any constant accuracy in time nO(S2), even in the arbitrary noise (“agnostic”) model. Complementing this, we also show that any learning algorithm for CS information-theoretically requires 2Ω(S2) examples for learning to constant accuracy. These results together show that Gaussian surface area essentially characterizes the computational complexity of learning under the Gaussian distribution.