Risk-based generalizations of f-divergences

Darío García-García; Ulrike Von Luxburg; Raúl Santos-Rodríguez

Risk-based generalizations of f-divergences

Darío García-García^*
, Ulrike Von Luxburg
, Raúl Santos-Rodríguez

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

10 Citations (Scopus)

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/-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.

Original language	English
Title of host publication	Proceedings of the 28th International Conference on Machine Learning, ICML 2011
Pages	417-424
Number of pages	8
Publication status	Published - 7 Oct 2011
Event	28th International Conference on Machine Learning, ICML 2011 - Bellevue, WA, United Kingdom Duration: 28 Jun 2011 → 2 Jul 2011

Conference

Conference	28th International Conference on Machine Learning, ICML 2011
Country/Territory	United Kingdom
City	Bellevue, WA
Period	28/06/11 → 2/07/11

Handle.net

Persistent link

Cite this

@inproceedings{b46b2b572f374ce9862dcba99fc60157,

title = "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/-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.",

author = "Dar{\'i}o Garc{\'i}a-Garc{\'i}a and \{Von Luxburg\}, Ulrike and Ra{\'u}l Santos-Rodr{\'i}guez",

year = "2011",

month = oct,

day = "7",

language = "English",

isbn = "9781450306195",

pages = "417--424",

booktitle = "Proceedings of the 28th International Conference on Machine Learning, ICML 2011",

note = "28th International Conference on Machine Learning, ICML 2011 ; Conference date: 28-06-2011 Through 02-07-2011",

}

TY - GEN

T1 - Risk-based generalizations of f-divergences

AU - García-García, Darío

AU - Von Luxburg, Ulrike

AU - Santos-Rodríguez, Raúl

PY - 2011/10/7

Y1 - 2011/10/7

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/80053460732

M3 - Conference Contribution (Conference Proceeding)

AN - SCOPUS:80053460732

SN - 9781450306195

SP - 417

EP - 424

BT - Proceedings of the 28th International Conference on Machine Learning, ICML 2011

T2 - 28th International Conference on Machine Learning, ICML 2011

Y2 - 28 June 2011 through 2 July 2011

ER -

Risk-based generalizations of f-divergences

Abstract

Conference

Handle.net

Other files and links

Fingerprint

Cite this