A Refinement of Vapnik--Chervonenkis' Theorem

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Iosevich, A., Vagharshakyan, A., Wyman, E.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912842917085184
author Iosevich, A.
Vagharshakyan, A.
Wyman, E.
author_facet Iosevich, A.
Vagharshakyan, A.
Wyman, E.
contents Vapnik--Chervonenkis' theorem is a seminal result in machine learning. It establishes sufficient conditions for empirical probabilities to converge to theoretical probabilities, uniformly over families of events. It also provides an estimate for the rate of such uniform convergence. We revisit the probabilistic component of the classical argument. Instead of applying Hoeffding's inequality at the final step, we use a normal approximation with explicit Berry--Esseen error control. This yields a moderate-deviation sharpening of the usual VC estimate, with an additional factor of order $(\varepsilon\sqrt{n})^{-1}$ in the leading exponential term when $\varepsilon\sqrt{n}$ is large.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16411
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Refinement of Vapnik--Chervonenkis' Theorem
Iosevich, A.
Vagharshakyan, A.
Wyman, E.
Machine Learning
Classical Analysis and ODEs
Probability
68Q32
Vapnik--Chervonenkis' theorem is a seminal result in machine learning. It establishes sufficient conditions for empirical probabilities to converge to theoretical probabilities, uniformly over families of events. It also provides an estimate for the rate of such uniform convergence. We revisit the probabilistic component of the classical argument. Instead of applying Hoeffding's inequality at the final step, we use a normal approximation with explicit Berry--Esseen error control. This yields a moderate-deviation sharpening of the usual VC estimate, with an additional factor of order $(\varepsilon\sqrt{n})^{-1}$ in the leading exponential term when $\varepsilon\sqrt{n}$ is large.
title A Refinement of Vapnik--Chervonenkis' Theorem
topic Machine Learning
Classical Analysis and ODEs
Probability
68Q32
url https://arxiv.org/abs/2601.16411