DocumentCode :
1765511
Title :
Covering Numbers for Convex Functions
Author :
Guntuboyina, Adityanand ; Sen, Baha
Author_Institution :
Dept. of Stat., Univ. of California, Berkeley, Berkeley, CA, USA
Volume :
59
Issue :
4
fYear :
2013
fDate :
41365
Firstpage :
1957
Lastpage :
1965
Abstract :
In this paper, we study the covering numbers of the space of convex and uniformly bounded functions in multidimension. We find optimal upper and lower bounds for the ε-covering number of C([a, b]d, B), in the Lp-metric, 1 ≤ p <; ∞, in terms of the relevant constants, where d ≥ 1, a <; b ∈ ℝ, B > 0, and C([a, b]d, B) denotes the set of all convex functions on that are uniformly bounded by B. We summarize previously known results on covering numbers for convex functions and also provide alternate proofs of some known results. Our results have direct implications in the study of rates of convergence of empirical minimization procedures as well as optimal convergence rates in the numerous convexity constrained function estimation problems.
Keywords :
convergence; entropy; minimisation; convex function; covering numbers; empirical minimization procedures; numerous convexity constrained function estimation problem; optimal convergence rate; uniform bounded function; Convergence; Convex functions; Estimation; Materials; Measurement; Minimization; Upper bound; $L_{p}$-metric; Convexity constrained function estimation; Hausdorff distance; Kolmogorov entropy; empirical risk minimization; metric entropy; packing numbers;
fLanguage :
English
Journal_Title :
Information Theory, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9448
Type :
jour
DOI :
10.1109/TIT.2012.2235172
Filename :
6392278
Link To Document :
بازگشت