Combinatorial bounds on the α-divergence of univariate mixture models

Frank Nielsen; Ke Sun

ICASSP 2017accepted0 citations

Combinatorial bounds on the α-divergence of univariate mixture models

Abstract

We derive lower- and upper-bounds of α-divergence between univariate mixture models with components in the exponential family. Three pairs of bounds are presented in order with increasing quality and increasing computational cost. They are verified empirically through simulated Gaussian mixture models. The presented methodology generalizes to other divergence families relying on Hellinger-type integrals.

BibTeX

@inproceedings{icassp2017_combinatorialbou,
  title = {Combinatorial bounds on the α-divergence of univariate mixture models},
  author = {Frank Nielsen and Ke Sun},
  booktitle = {ICASSP 2017},
  year = {2017}
}