Information Geometry of the Gaussian Space
Probability
2018-03-23 v1
Abstract
We discuss the Pistone-Sempi exponential manifold on the finite-dimensional Gaussian space. We consider the role of the entropy, the continuity of translations, Poincar\'e-type inequalities, the generalized differentiability of probability densities of the Gaussian space.
Keywords
Cite
@article{arxiv.1803.08135,
title = {Information Geometry of the Gaussian Space},
author = {Giovanni Pistone},
journal= {arXiv preprint arXiv:1803.08135},
year = {2018}
}
Comments
Extendexd version of the paper presented at the IGAIA IV Conference 2016. Submitted for publication in the conference proceedings