Thomas Bayes' walk on manifolds
Statistics Theory
2012-06-05 v1 Statistics Theory
Abstract
Convergence of the Bayes posterior measure is considered in canonical statistical settings where observations sit on a geometrical object such as a compact manifold, or more generally on a compact metric space verifying some conditions. A natural geometric prior based on randomly rescaled solutions of the heat equation is considered. Upper and lower bound posterior contraction rates are derived.
Cite
@article{arxiv.1206.0459,
title = {Thomas Bayes' walk on manifolds},
author = {Ismael Castillo and Gerard Kerkyacharian and Dominique Picard},
journal= {arXiv preprint arXiv:1206.0459},
year = {2012}
}