Skip to content
conftrace_
2012 AISTATS AISTATS 2012

Error bounds for Kernel Fisher Linear Discriminant in Gaussian Hilbert space

Abstract

We give a non-trivial, non-asymptotic upper bound on the classification error of the popular Kernel Fisher Linear Discriminant classifier under the assumption that the kernel-induced space is a Gaussian Hilbert space.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Mathematics & Optimization

Authors

Robert Durrant, Ata Kaban

Topics

Machine Learning > Core Methods > Classification Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Optimization & Theory > Statistical Learning Mathematics & Optimization > Optimization > Stochastic Methods Machine Learning > Core Methods > Kernel Methods

Keywords

classification error error bound kernel fisher linear discriminant gaussian hilbert space kernel-induced space kernel methods
Download PDF

More from AISTATS 2012

All AISTATS 2012 papers →
A metric learning perspective of SVM: on the relation of LMNN and SVM
Generic Methods for Optimization-Based Modeling
Lifted coordinate descent for learning with trace-norm regularization
Copula Network Classifiers (CNCs)
Lightning-speed Structure Learning of Nonlinear Continuous Networks
Statistical test for consistent estimation of causal effects in linear non-Gaussian models