Metrics defined by Bregman divergences: Part 2
Chen, P. ; Chen, Y. ; Rao, M.
Commun. Math. Sci., Tome 6 (2008) no. 1, p. 927-948 / Harvested from Project Euclid
Bregman divergences have played an important role in many research areas. Divergence is a measure of dissimilarity and by itself is not a metric. If a function of the divergence is a metric, then it becomes much more powerful. In Part 1 we have given necessary and sufficient conditions on the convex function in order that the square root of the averaged associated divergence is a metric. In this paper we provide a min-max approach to getting a metric from Bregman divergence. We show that the “capacity” to the power 1/e is a metric.
Publié le : 2008-12-15
Classification:  Metrics,  Bregman divergence,  triangle inequality,  Kullback-Leibler divergence,  Shannon entropy,  capacity,  26D10,  94A15
@article{1229619677,
     author = {Chen, P. and Chen, Y. and Rao, M.},
     title = {Metrics defined by Bregman divergences: Part 2},
     journal = {Commun. Math. Sci.},
     volume = {6},
     number = {1},
     year = {2008},
     pages = { 927-948},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1229619677}
}
Chen, P.; Chen, Y.; Rao, M. Metrics defined by Bregman divergences: Part 2. Commun. Math. Sci., Tome 6 (2008) no. 1, pp.  927-948. http://gdmltest.u-ga.fr/item/1229619677/