On a convergence property of a geometrical algorithm for statistical manifolds
Machine Learning
2019-09-30 v1 Machine Learning
Abstract
In this paper, we examine a geometrical projection algorithm for statistical inference. The algorithm is based on Pythagorean relation and it is derivative-free as well as representation-free that is useful in nonparametric cases. We derive a bound of learning rate to guarantee local convergence. In special cases of m-mixture and e-mixture estimation problems, we calculate specific forms of the bound that can be used easily in practice.
Keywords
Cite
@article{arxiv.1909.12644,
title = {On a convergence property of a geometrical algorithm for statistical manifolds},
author = {Shotaro Akaho and Hideitsu Hino and Noboru Murata},
journal= {arXiv preprint arXiv:1909.12644},
year = {2019}
}