Empirical Processes Indexed by Lipschitz Functions
نویسندگان
چکیده
منابع مشابه
Empirical processes indexed by estimated functions
We consider the convergence of empirical processes indexed by functions that depend on an estimated parameter η and give several alternative conditions under which the “estimated parameter” ηn can be replaced by its natural limit η0 uniformly in some other indexing set Θ. In particular we reconsider some examples treated by Ghoudi and Remillard [Asymptotic Methods in Probability and Statistics ...
متن کاملWeak convergence of empirical copula processes indexed by functions
DRAGAN RADULOVIĆ1, MARTEN WEGKAMP2 and YUE ZHAO3 1Department of Mathematics, Florida Atlantic University, 777 Glades Road, Boca Raton, FL 33431, USA. E-mail: [email protected] 2Department of Mathematics and Department of Statistical Science, Cornell University, 432 Malott Hall, Ithaca, NY 14853, USA. E-mail: [email protected] 3Department of Statistical Science, Cornell University, 310 M...
متن کاملRates of Growth and Sample Moduli for Weighted Empirical Processes Indexed by Sets
Probability inequalities are. obtained for the supremum of a weighted empirical process indexed. by a Vapnik-Cervonenkis class C of sets. These inequalities are particularly useful under the assumption P(ufC E: C : P(C) < t D -? 0 as t -? o. They are used to obtain almost sure bounds on the rate of growth of the process as the sample size approaches infinity, to find an asymptotic sample modulu...
متن کاملControlling Lipschitz functions
Given any positive integers m and d, we say the a sequence of points (xi)i∈I in Rm is Lipschitz-d-controlling if one can select suitable values yi (i ∈ I) such that for every Lipschitz function f : Rm → Rd there exists i with |f(xi)−yi| < 1. We conjecture that for every m ≤ d, a sequence (xi)i∈I ⊂ Rm is d-controlling if and only if sup n∈N |{i ∈ I : |xi| ≤ n}| nd =∞. We prove that this conditio...
متن کاملInterpolation of Lipschitz functions
This paper describes a new computational approach to multivariate scattered data interpolation. It is assumed that the data is generated by a Lipschitz continuous function f. The proposed approach uses the central interpolation scheme, which produces an optimal interpolant in the worst case scenario. It provides best uniform error bounds on f, and thus translates into reliable learning of f. Th...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Annals of Probability
سال: 1986
ISSN: 0091-1798
DOI: 10.1214/aop/1176992373