Risk-based generalizations of f-divergences
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.