Entropy and the Combinatorial Dimension
arXiv:math/0203275
Abstract
We solve Talagrand's entropy problem: the L_2-covering numbers of every uniformly bounded class of functions are exponential in its shattering dimension. This extends Dudley's theorem on classes of {0,1}-valued functions, for which the shattering dimension is the Vapnik-Chervonenkis dimension. In convex geometry, the solution means that the entropy of a convex body K is controlled by the maximal dimension of a cube of a fixed side contained in the coordinate projections of K. This has a number of consequences, including the optimal Elton's Theorem and estimates on the uniform central limit theorem in the real valued case.
arXiv commentA final version of the paper (Inventiones Math., to appear) Only two applications added: one to Asymptotic Geometry (the optimal Elton Theorem) and the other to empirical processes (the uniform central limit theorem)