English

Entropy Estimate For High Dimensional Monotonic Functions

Statistics Theory 2007-06-13 v1 Classical Analysis and ODEs Statistics Theory

Abstract

We establish upper and lower bounds for the metric entropy and bracketing entropy of the class of dd-dimensional bounded monotonic functions under LpL^p norms. It is interesting to see that both the metric entropy and bracketing entropy have different behaviors for p<d/(d1)p<d/(d-1) and p>d/(d1)p>d/(d-1). We apply the new bounds for bracketing entropy to establish a global rate of convergence of the MLE of a dd-dimensional monotone density.

Keywords

Cite

@article{arxiv.math/0512641,
  title  = {Entropy Estimate For High Dimensional Monotonic Functions},
  author = {Fuchang Gao and Jon A. Wellner},
  journal= {arXiv preprint arXiv:math/0512641},
  year   = {2007}
}

Comments

11 pages. Submitted to Journal of Multivariate Analysis. See also http://www.stat.washington.edu/jaw/RESEARCH/PAPERS/available.html