Skip navigation
Skip navigation

Risk-based generalizations of f-divergences

Garcia-Garcia, Dario; von Luxburg, Ulrike; Santos-Rodriguez, Raul

Description

We derive a generalized notion of f-divergences, called (f,l)-divergences. We show that this generalization enjoys many of the nice properties of/-divergences, although it is a richer family. It also provides alternative definitions of standard divergences in terms of surrogate risks. As a first practical application of this theory, we derive a new estimator for the Kulback-Leibler divergence that we use for clustering sets of vectors.

CollectionsANU Research Publications
Date published: 2011
Type: Conference paper
URI: http://hdl.handle.net/1885/17402
Source: Max-margin Learning for Lower Linear Envelope Potentials in Binary Markov Random Fields

Download

File Description SizeFormat Image
01_Garcia-Garcia_Risk-based_generalizations_of_2011.pdf170.56 kBAdobe PDF    Request a copy
02_Garcia-Garcia_Risk-based_generalizations_of_2011.pdf272.11 kBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  12 November 2018/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator