PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Risk-based generalizations of f-divergences
Dario Garcia-Garcia, Ulrike v. Luxburg and Raul Santos-Rodriguez
In: ICML 2011(2011).


We derive a generalized notion of f- divergences, called (f, l)-divergences. We show that this generalization enjoys many of the nice properties of f -divergences, although it is a richer family. It also provides alter- native 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.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:8634
Deposited By:Ulrike Von Luxburg
Deposited On:16 February 2012