Skip to main content
Log in

Entropy and the combinatorial dimension

  • Published:
Inventiones mathematicae Aims and scope

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.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

Author information

Authors and Affiliations

Authors

Additional information

Oblatum 10-XII-2001 & 4-IX-2002¶Published online: 8 November 2002

Rights and permissions

Reprints and permissions

About this article

Cite this article

Mendelson, S., Vershynin, R. Entropy and the combinatorial dimension. Invent. math. 152, 37–55 (2003). https://doi.org/10.1007/s00222-002-0266-3

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00222-002-0266-3

Keywords

Navigation