Quasiconvex Jensen Divergences and Quasiconvex Bregman Divergences
| Autor: | Gaëtan Hadjeres, Frank Nielsen |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | Springer Proceedings in Mathematics & Statistics ISBN: 9783030779566 SPIGL |
| DOI: | 10.1007/978-3-030-77957-3_11 |
| Popis: | We first introduce the class of strictly quasiconvex and strictly quasiconcave Jensen divergences which are asymmetric distances, and study some of their properties. We then define the strictly quasiconvex Bregman divergences as the limit case of scaled and skewed quasiconvex Jensen divergences, and report a simple closed-form formula which shows that these divergences are only pseudo-divergences at countably many inflection points of the quasiconvex generators. To remedy this problem, we propose the \(\delta \)-averaged quasiconvex Bregman divergences which integrate the pseudo-divergences over a small neighborhood in order obtain a proper divergence. The formula of \(\delta \)-averaged quasiconvex Bregman divergences extend even to non-differentiable strictly quasiconvex generators. These quasiconvex Bregman divergences between distinct elements have the property to always have one orientation finite while the reverse orientation is infinite. We show that these quasiconvex Bregman divergences can also be interpreted as limit cases of generalized skewed Jensen divergences with respect to comparative convexity by using power means. Finally, we illustrate how these quasiconvex Bregman divergences naturally appear as equivalent divergences for the Kullback-Leibler divergences between probability densities belonging to a same parametric family of distributions with nested density supports. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|