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

01/07/2022
by   Masahito Hayashi, et al.
0

We formulate em algorithm in the framework of Bregman divergence, which is a general problem setting of information geometry. That is, we address the minimization problem of the Bregman divergence between an exponential subfamily and a mixture subfamily in a Bregman divergence system. Then, we show the convergence and its speed under several conditions. We apply this algorithm to rate distortion and its variants including the quantum setting, and show the usefulness of our general algorithm.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/23/2020

Maximizing the Bregman divergence from a Bregman family

The problem to maximize the information divergence from an exponential f...
research
02/14/2019

Geometry of Arimoto Algorithm

This paper aims to reveal information geometric structure of Arimoto alg...
research
02/14/2023

Minimization on mixture family

Iterative minimization algorithms appear in various areas including mach...
research
11/02/2020

Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent

Expectation maximization (EM) is the default algorithm for fitting proba...
research
01/14/2022

Test-measured Rényi divergences

One possibility of defining a quantum Rényi α-divergence of two quantum ...
research
09/04/2018

Analysis for the Slow Convergence in Arimoto Algorithm

In this paper, we investigate the convergence speed of the Arimoto algor...
research
03/09/2021

Monotonic Alpha-divergence Minimisation

In this paper, we introduce a novel iterative algorithm which carries ou...

Please sign up or login with your details

Forgot password? Click here to reset