PAC-Learning with general class noise models

Authors:
Shahin Jabbari;Robert C. Holte;Sandra Zilles
Affiliations:
University of California, Los Angeles;University of Alberta, Canada;University of Regina, Canada
Venue:
KI'12 Proceedings of the 35th Annual German conference on Advances in Artificial Intelligence
Year:
2012

Citing 13
Cited 0

Classifying learnable geometric concepts with the Vapnik-Chervonenkis dimension

STOC '86 Proceedings of the eighteenth annual ACM symposium on Theory of computing
Learning from good and bad data

Learning from good and bad data
Decision theoretic generalizations of the PAC model for neural net and other learning applications

Information and Computation
Toward Efficient Agnostic Learning

Machine Learning - Special issue on computational learning theory, COLT'92
Four types of noise in data for PAC learning

Information Processing Letters
The nature of statistical learning theory

The nature of statistical learning theory
Efficient noise-tolerant learning from statistical queries

Journal of the ACM (JACM)
PAC learning with nasty noise

Theoretical Computer Science
Learning From Noisy Examples

Machine Learning
PAC Learning with Constant-Partition Classification Noise and Applications to Decision Tree Induction

ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
A theory of the learnable

STOC '84 Proceedings of the sixteenth annual ACM symposium on Theory of computing
CN = CPCN

ICML '06 Proceedings of the 23rd international conference on Machine learning
Efficient distribution-free learning of probabilistic concepts

SFCS '90 Proceedings of the 31st Annual Symposium on Foundations of Computer Science

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce a framework for class noise, in which most of the known class noise models for the PAC setting can be formulated. Within this framework, we study properties of noise models that enable learning of concept classes of finite VC-dimension with the Empirical Risk Minimization (ERM) strategy. We introduce simple noise models for which classical ERM is not successful. Aiming at a more generalpurpose algorithm for learning under noise, we generalize ERM to a more powerful strategy. Finally, we study general characteristics of noise models that enable learning of concept classes of finite VC-dimension with this new strategy.