PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A Kernel Approach to Comparing Distributions
Arthur Gretton, Karsten M. Borgwardt, Malte Rasch, Bernhard Schölkopf and Alex Smola
In: AAAI07, 22-26 Jul 2007, Vancouver, Canada.

Abstract

We describe a technique for comparing distributions without the need for density estimation as an intermediate step. Our approach relies on mapping the distributions into a Reproducing Kernel Hilbert Space. We apply this technique to construct a two-sample test, which is used for determining whether two sets of observations arise from the same distribution. We use this test in attribute matching for databases using the Hungarian marriage method, where it performs strongly. We also demonstrate excellent performance when comparing distributions over graphs, for which no alternative tests currently exist.

EPrint Type:Conference or Workshop Item (Talk)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:3666
Deposited By:Malte Rasch
Deposited On:14 February 2008