PAC-Bayesian learning of linear classifiers

14 years 5 months ago

Download www2.ift.ulaval.ca

We present a general PAC-Bayes theorem from which all known PAC-Bayes risk bounds are obtained as particular cases. We also propose different learning algorithms for finding linear classifiers that minimize these bounds. These learning algorithms are generally competitive with both AdaBoost and the SVM.

Alexandre Lacasse, François Laviolette, Mar

Real-time Traffic

ICML 2009 | Machine Learning | PAC-Bayes Risk Bounds |

claim paper

» Boosting adaptive linear weak classifiers for online learning and tracking

» A Unifying Framework for Learning the Linear Combiners for Classifier Ensembles

» Confidenceweighted linear classification

» Probabilistic Classifiers and the Concepts They Recognize

» Learning to classify with missing and corrupted features

» Pareto optimal linear classification

» Feature shaping for linear SVM classifiers

» Manifold Based Local Classifiers Linear and Nonlinear Approaches

Post Info
More Details (n/a)

Added	17 Nov 2009
Updated	17 Nov 2009
Type	Conference
Year	2009
Where	ICML
Authors	Alexandre Lacasse, François Laviolette, Mario Marchand, Pascal Germain

Comments (0)

Sciweavers

PAC-Bayesian learning of linear classifiers

ICML 2009 | Machine Learning | PAC-Bayes Risk Bounds |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers