Combinatorial bounds on the α-divergence of univariate mixture models

Frank Nielsen, Ke Sun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

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.
Original languageEnglish (US)
Title of host publication2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages4476-4480
Number of pages5
ISBN (Print)9781509041176
DOIs
StatePublished - Jun 20 2017

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01

Fingerprint

Dive into the research topics of 'Combinatorial bounds on the α-divergence of univariate mixture models'. Together they form a unique fingerprint.

Cite this