Summary
The 2018 International Symposium on Information Theory and Its Applications　(ISITA2018)
2018
Session Number:We-PM-2-3
Session:
Number:We-PM-2-3.4
Analysis for the Slow Convergence in Arimoto Algorithm
Kenji Nakagawa, Yoshinori Takei, Kohei Watabe,
pp.764-768
Publication Date:2018/10/18
Online ISSN:2188-5079
DOI:10.34385/proc.55.We-PM-2-3.4
PDF download
Summary:
In this paper, we investigate the convergence speed of the Arimoto algorithm. By analyzing the Taylor expansion of the defining function of the Arimoto algorithm, we will clarify the conditions for the exponential or 1/N order convergence and calculate the convergence speed. We show that the convergence speed of the 1/N order is evaluated by the derivatives of the Kullback-Leibler divergence with respect to the input probabilities. The analysis for the convergence of the 1/N order is new in this paper. Based on the analysis, we will compare the convergence speed of the Arimoto algorithm with the theoretical values obtained in our theorems.