On the sample complexity of PAC learning half-spaces against the uniform distribution

Authors:
P. M. Long
Affiliations:
Res. Triangle Inst., Research Triangle Park, NC
Venue:
IEEE Transactions on Neural Networks
Year:
1995

Citing 0
Cited 11

On PAC learning using Winnow, Perceptron, and a Perceptron-like algorithm

COLT '99 Proceedings of the twelfth annual conference on Computational learning theory
An upper bound on the sample complexity of PAC-learning halfspaces with respect to the uniform distribution

Information Processing Letters
Agnostically Learning Halfspaces

FOCS '05 Proceedings of the 46th Annual IEEE Symposium on Foundations of Computer Science
A bound on the label complexity of agnostic active learning

Proceedings of the 24th international conference on Machine learning
A Uniform Lower Error Bound for Half-Space Learning

ALT '08 Proceedings of the 19th international conference on Algorithmic Learning Theory
Agnostic active learning

Journal of Computer and System Sciences
Using the doubling dimension to analyze the generalization of learning algorithms

Journal of Computer and System Sciences
Margin based active learning

COLT'07 Proceedings of the 20th annual conference on Learning theory
The regularized least squares algorithm and the problem of learning halfspaces

Information Processing Letters
Efficient algorithms for general active learning

COLT'06 Proceedings of the 19th annual conference on Learning Theory
Analysis of perceptron-based active learning

COLT'05 Proceedings of the 18th annual conference on Learning Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

We prove an Ω(d/ε+1/εlog1/δ) lower bound on the PAC (probably approximately correct) learning sample complexity of learning half-spaces against the uniform distribution on the unit ball in Rd