On the Size of Convex Hulls of Small Sets
Shahar Mendelson;
2(Oct):1-18, 2001.
Abstract
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.
[abs]
[pdf]
[ps.gz]
[ps]