Skip to content
conftrace_
2001 JMLR JMLR 2001

On the Size of Convex Hulls of Small Sets

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]

🌱 Topic Pioneer - Learning Theory
📈 Trend Setter - Dimensionality Reduction
🧭 Keyword Pioneer - learning theory
🐣 Hot Topic Early Bird - learning theory

Authors

Shahar Mendelson

Topics

Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Optimization & Theory > Statistical Learning Machine Learning > Optimization & Theory > Theory Machine Learning > Core Methods > Dimensionality Reduction

Keywords

learning theory fat-shattering dimension convex hull covering number
Download PDF

More from JMLR 2001

All JMLR 2001 papers →
Bayes Point Machines
Tracking the Best Linear Predictor
Prior Knowledge and Preferential Structures in Gradient Descent Learning Algorithms
Graph-Based Hierarchical Conceptual Clustering
Support Vector Machine Active Learning with Applications to Text Classification
On the Influence of the Kernel on the Consistency of Support Vector Machines