English

Information Geometry of smooth densities on the Gaussian space: Poincar\'e inequalities

Statistics Theory 2021-01-11 v2 Statistics Theory

Abstract

We derive bounds for the Orlicz norm of the deviation of a random variable defined on Rn\mathbb{R}^n from its Gaussian mean value. The random variables are assumed to be smooth and the bound itself depends on the Orlicz norm of the gradient. Applications to non-parametric Information Geometry are discussed.

Keywords

Cite

@article{arxiv.2002.12871,
  title  = {Information Geometry of smooth densities on the Gaussian space: Poincar\'e inequalities},
  author = {Giovanni Pistone},
  journal= {arXiv preprint arXiv:2002.12871},
  year   = {2021}
}

Comments

Accepted. Minor corrections