Uniform approximation of Vapnik-Chervonenkis classes
نویسندگان
چکیده
For any family of measurable sets in a probability space, we show that either (i) the family has infinite Vapnik–Chervonenkis (VC) dimension or (ii) for every ε > 0 there is a finite partition π such the essential π -boundary of each set has measure at most ε. Immediate corollaries include the fact that a separable family with finite VC dimension has finite bracketing numbers, and satisfies uniform laws of large numbers for every ergodic process. From these corollaries, we derive analogous results for VC major and VC graph families of functions.
منابع مشابه
On Martingale Extensions of Vapnik-Chervonenkis Theory with Applications to Online Learning
We review recent advances on uniform martingale laws of large numbers and the associated sequential complexity measures. These results may be considered as forming a non-i.i.d. generalization of Vapnik-Chervonenkis theory. We discuss applications to online learning, provide a recipe for designing online learning algorithms, and illustrate the techniques on the problem of online node classificat...
متن کاملSign rank versus Vapnik-Chervonenkis dimension
This work studies the maximum possible sign rank of sign (N ×N)-matrices with a given Vapnik-Chervonenkis dimension d. For d = 1, this maximum is three. For d = 2, this maximum is Θ̃(N). For d > 2, similar but slightly less accurate statements hold. The lower bounds improve on previous ones by Ben-David et al., and the upper bounds are novel. The lower bounds are obtained by probabilistic constr...
متن کاملVapnik-chervonenkis Classes of Definable Sets
We show that a class of subsets of a structure uniformly definable by a first-order formula is a Vapnik-Chervonenkis class if and only if the formula does not have the independence property. Via this connection we obtain several new examples of Vapnik-Chervonenkis classes, including sets of positivity of finitely subanalytic functions.
متن کاملVapnik-Chervonenkis Density in Some Theories without the Independence Property, II
We study the Vapnik-Chervonenkis (VC) density of definable families in certain stable first-order theories. In particular we obtain uniform bounds on VC density of definable families in finite U-rank theories without the finite cover property, and we characterize those abelian groups for which there exist uniform bounds on the VC density of definable families.
متن کاملError Bounds for Real Function Classes Based on Discretized Vapnik-Chervonenkis Dimensions
The Vapnik-Chervonenkis (VC) dimension plays an important role in statistical learning theory. In this paper, we propose the discretized VC dimension obtained by discretizing the range of a real function class. Then, we point out that Sauer’s Lemma is valid for the discretized VC dimension. We group the real function classes having the infinite VC dimension into four categories by using the dis...
متن کامل