AI Chat AI Image Generator AI Video Text to Speech

Maximizing the Bregman divergence from a Bregman family

01/23/2020
∙
by   Johannes Rauh, et al.
∙
0
∙

The problem to maximize the information divergence from an exponential family is generalized to the setting of Bregman divergences and suitably defined Bregman families.

READ FULL TEXT

page 1

page 2

page 3

page 4

Related Research

research
∙ 07/26/2021

Tsallis and Rényi deformations linked via a new λ-duality

Tsallis and Rényi entropies, which are monotone transformations of such ...
0 Ting-Kam Leonard Wong, et al. ∙
research
∙ 02/22/2022

The duo Fenchel-Young divergence

By calculating the Kullback-Leibler divergence between two probability m...
0 Frank Nielsen, et al. ∙
research
∙ 01/18/2019

Gambling and Rényi Divergence

For gambling on horses, a one-parameter family of utility functions is p...
0 Cédric Bleuler, et al. ∙
research
∙ 01/07/2022

Bregman divergence based em algorithm and its application to classical and quantum rate distortion theory

We formulate em algorithm in the framework of Bregman divergence, which ...
0 Masahito Hayashi, et al. ∙
research
∙ 11/07/2020

When Optimizing f-divergence is Robust with Label Noise

We show when maximizing a properly defined f-divergence measure with res...
0 Jiaheng Wei, et al. ∙
research
∙ 10/09/2014

Distributed Estimation, Information Loss and Exponential Families

Distributed learning of probabilistic models from multiple data reposito...
0 Qiang Liu, et al. ∙
research
∙ 08/11/2020

Conditions for the existence of a generalization of Rényi divergence

We give necessary and sufficient conditions for the existence of a gener...
0 Rui F. Vigelis, et al. ∙

Please sign up or login with your details

Forgot password? Click here to reset

Out of credits

Refill your membership to continue using DeepAI

Stripe
Paypal