arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1809.00752cs.ITmath.IT
收藏

Arimoto算法收敛速度慢的原因分析

Analysis for the Slow Convergence in Arimoto Algorithm

Kenji Nakagawa, Yoshinori Takei, Kohei Watabe

摘要:

本文研究了Arimoto算法的收敛速度。通过分析Arimoto算法定义函数的Taylor展开式,阐明了指数阶或$1/N$阶收敛的条件,并计算了收敛速度。我们证明了$1/N$阶的收敛速度是由Kullback-Leibler发散相对于输入概率的导数来估计的。本文对$1/N$阶的收敛性进行了新的分析。基于分析,我们将比较Arimoto算法的收敛速度与我们的定理中得到的理论值几个信道矩阵。

英文摘要:

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 for several channel matrices.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑