Projections with logarithmic divergences

DOI10.1007/978-3-030-80209-7_52MaRDI QIDQ6367819arXivFDO

Authors Zhixu Tao, Ting-Kam Leonard Wong

Publication date 8 May 2021

Published in arXiv

Full work available at URL https://doi.org/10.1007/978-3-030-80209-7_52

Mathematics Subject Classification ID

Differential geometric aspects of statistical manifolds and information geometry (53B12) Information geometry (statistical aspects) (62B11)

arXiv classification

math.DGstat.ME

Abstract: In information geometry, generalized exponential families and statistical manifolds with curvature are under active investigation in recent years. In this paper we consider the statistical manifold induced by a logarithmic $L^{(alpha)}$-divergence which generalizes the Bregman divergence. It is known that such a manifold is dually projectively flat with constant negative sectional curvature, and is closely related to the $mathcal{F}^{(alpha)}$-family, a generalized exponential family introduced by the second author. Our main result constructs a dual foliation of the statistical manifold, i.e., an orthogonal decomposition consisting of primal and dual autoparallel submanifolds. This decomposition, which can be naturally interpreted in terms of primal and dual projections with respect to the logarithmic divergence, extends the dual foliation of a dually flat manifold studied by Amari. As an application, we formulate a new $L^{(alpha)}$-PCA problem which generalizes the exponential family PCA.

This page was built for publication: Projections with logarithmic divergences

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6367819)