Combinatorial bounds on the α-divergence of univariate mixture models
Type
Conference PaperAuthors
Nielsen, FrankSun, Ke
Date
2017-06-20Online Publication Date
2017-06-20Print Publication Date
2017-03Permanent link to this record
http://hdl.handle.net/10754/625623
Metadata
Show full item recordAbstract
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.Citation
Nielsen F, Sun K (2017) Combinatorial bounds on the α-divergence of univariate mixture models. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Available: http://dx.doi.org/10.1109/ICASSP.2017.7953003.Conference/Event name
2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017Additional Links
http://ieeexplore.ieee.org/document/7953003/ae974a485f413a2113503eed53cd6c53
10.1109/ICASSP.2017.7953003