The local geometry of finite mixtures
Statistics Theory
2015-02-04 v2 Statistics Theory
Abstract
We establish that for q>=1, the class of convex combinations of q translates of a smooth probability density has local doubling dimension proportional to q. The key difficulty in the proof is to control the local geometric structure of mixture classes. Our local geometry theorem yields a bound on the (bracketing) metric entropy of a class of normalized densities, from which a local entropy bound is deduced by a general slicing procedure.
Keywords
Cite
@article{arxiv.1202.3482,
title = {The local geometry of finite mixtures},
author = {Elisabeth Gassiat and Ramon Van Handel},
journal= {arXiv preprint arXiv:1202.3482},
year = {2015}
}
Comments
25 pages