Skip navigation
Skip navigation

On the size of convex hulls of small sets

Mendelson, Shahar

Description

We investigate two different notions of "size" which appear naturally in Statistical Learning Theory. We present quantitative estimates on the fat-shattering dimension and on the covering numbers of convex hulls of sets of functions, given the necessary data on the original sets. The proofs we present are relatively simple since they do not require extensive background in convex geometry.

CollectionsANU Research Publications
Date published: 2001-10
Type: Journal article
URI: http://hdl.handle.net/10440/304
http://digitalcollections.anu.edu.au/handle/10440/304
Source: Journal of Machine Learning Research

Download

File Description SizeFormat Image
Mendelson_Onthesize2001.pdf289.49 kBAdobe PDFThumbnail


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  23 August 2018/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator