Tighter Variational Representations of f-Divergences via Restriction to Probability Measures
Machine Learning
2012-06-22 v1 Machine Learning
Abstract
We show that the variational representations for f-divergences currently used in the literature can be tightened. This has implications to a number of methods recently proposed based on this representation. As an example application we use our tighter representation to derive a general f-divergence estimator based on two i.i.d. samples and derive the dual program for this estimator that performs well empirically. We also point out a connection between our estimator and MMD.
Keywords
Cite
@article{arxiv.1206.4664,
title = {Tighter Variational Representations of f-Divergences via Restriction to Probability Measures},
author = {Avraham Ruderman and Mark Reid and Dario Garcia-Garcia and James Petterson},
journal= {arXiv preprint arXiv:1206.4664},
year = {2012}
}
Comments
ICML2012