On the size of convex hulls of small sets
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.
|Collections||ANU Research Publications|
|Source:||Journal of Machine Learning Research|
|Mendelson_Onthesize2001.pdf||289.49 kB||Adobe PDF|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.