Risk-Based Generalizations of F-Divergences

Abstract

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 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.

Cite

Text

García-García et al. "Risk-Based Generalizations of F-Divergences." International Conference on Machine Learning, 2011.

Markdown

[García-García et al. "Risk-Based Generalizations of F-Divergences." International Conference on Machine Learning, 2011.](https://mlanthology.org/icml/2011/garciagarcia2011icml-risk/)

BibTeX

@inproceedings{garciagarcia2011icml-risk,
  title     = {{Risk-Based Generalizations of F-Divergences}},
  author    = {García-García, Dario and von Luxburg, Ulrike and Santos-Rodríguez, Raúl},
  booktitle = {International Conference on Machine Learning},
  year      = {2011},
  pages     = {417-424},
  url       = {https://mlanthology.org/icml/2011/garciagarcia2011icml-risk/}
}