Maximal width learning of binary functions

Authors:
Martin Anthony;Joel Ratsaby
Affiliations:
Department of Mathematics, London School of Economics, Houghton Street, London WC2A2AE, UK;Electrical and Electronics Engineering Department, Ariel University Center of Samaria, Ariel 40700, Israel
Venue:
Theoretical Computer Science
Year:
2010

Citing 7
Cited 2

Learnability and the Vapnik-Chervonenkis dimension

Journal of the ACM (JACM)
Efficient distribution-free learning of probabilistic concepts

Journal of Computer and System Sciences - Special issue: 31st IEEE conference on foundations of computer science, Oct. 22–24, 1990
Scale-sensitive dimensions, uniform convergence, and learnability

Journal of the ACM (JACM)
Learning in Neural Networks: Theoretical Foundations

Learning in Neural Networks: Theoretical Foundations
Function Learning from Interpolation

Combinatorics, Probability and Computing
Covering numbers for real-valued function classes

IEEE Transactions on Information Theory
The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network

IEEE Transactions on Information Theory

Robust cutpoints in the logical analysis of numerical data

Discrete Applied Mathematics
Learning bounds via sample width for classifiers on finite metric spaces

Theoretical Computer Science

Quantified Score

Hi-index	5.23

Visualization

Abstract

This paper concerns learning binary-valued functions defined on R, and investigates how a particular type of 'regularity' of hypotheses can be used to obtain better generalization error bounds. We derive error bounds that depend on the sample width (a notion analogous to that of sample margin for real-valued functions). This motivates learning algorithms that seek to maximize sample width.