Geometry of Arimoto Algorithm

02/14/2019
by   Shoji Toyota, et al.
0

This paper aims to reveal information geometric structure of Arimoto algorithm. In the process, a new algorithm that monotonically increases the Kullback-Leibler divergence is proposed, which is called `the Backward em-algorithm.'

READ FULL TEXT

page 1

page 2

page 3

page 4

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 ...
research
11/06/2016

EM Algorithm and Stochastic Control in Economics

Generalising the idea of the classical EM algorithm that is widely used ...
research
03/19/2021

Forward and Backward Bellman equations improve the efficiency of EM algorithm for DEC-POMDP

Decentralized partially observable Markov decision process (DEC-POMDP) m...
research
11/21/2017

On the EM-Tau algorithm: a new EM-style algorithm with partial E-steps

The EM algorithm is one of many important tools in the field of statisti...
research
08/17/2011

A Novel and Robust Evolution Algorithm for Optimizing Complicated Functions

In this paper, a novel mutation operator of differential evolution algor...
research
11/16/2022

Minimum information divergence of Q-functions for dynamic treatment resumes

This paper aims at presenting a new application of information geometry ...
research
03/28/2017

Convergence of the Forward-Backward Algorithm: Beyond the Worst Case with the Help of Geometry

We provide a comprehensive study of the convergence of forward-backward ...

Please sign up or login with your details

Forgot password? Click here to reset