English

Examples of Application of Nonparametric Information Geometry to Statistical Physics

Statistics Theory 2015-06-17 v1 Mathematical Physics math.MP Statistics Theory

Abstract

We review a nonparametric version of Amari's Information Geometry in which the set of positive probability densities on a given sample space is endowed with an atlas of charts to form a differentiable manifold modeled on Orlicz Banach spaces. This nonparametric setting is used to discuss the setting of typical problems in Machine Learning and Statistical Physics, such as relaxed optimization, Kullback-Leibler divergence, Boltzmann entropy, Boltzmann equation

Keywords

Cite

@article{arxiv.1308.5312,
  title  = {Examples of Application of Nonparametric Information Geometry to Statistical Physics},
  author = {Giovanni Pistone},
  journal= {arXiv preprint arXiv:1308.5312},
  year   = {2015}
}

Comments

24 pages