Literature DB >> 29658960

Entropy of Convex Functions on ℝ d.

Fuchang Gao1, Jon A Wellner2.   

Abstract

Let Ω be a bounded closed convex set in ℝ d with non-empty interior, and let 𝒞 r (Ω) be the class of convex functions on Ω with Lr -norm bounded by 1. We obtain sharp estimates of the ε-entropy of 𝒞 r (Ω) under Lp (Ω) metrics, 1 ≤ p < r ≤ ∞. In particular, the results imply that the universal lower bound ε-d/2 is also an upper bound for all d-polytopes, and the universal upper bound of [Formula: see text] for [Formula: see text] is attained by the closed unit ball. While a general convex body can be approximated by inscribed polytopes, the entropy rate does not carry over to the limiting body. Our results have applications to questions concerning rates of convergence of nonparametric estimators of high-dimensional shape-constrained functions.

Entities:  

Keywords:  bracketing entropy; convex functions; metric entropy; polytopes; simplicial approximation

Year:  2017        PMID: 29658960      PMCID: PMC5894528          DOI: 10.1007/s00365-017-9387-1

Source DB:  PubMed          Journal:  Constr Approx        ISSN: 0176-4276            Impact factor:   1.487


  1 in total

1.  On the rate of convergence of the maximum like-lihood estimator of a k-monotone density.

Authors:  Gao Fuchang; Wellner Jon A
Journal:  Sci China Ser A Math       Date:  2009-07
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.