A Refinement of Vapnik–Chervonenkis’ Theorem

arXiv:2601.16411v1 Announce Type: new
Abstract: 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 $(varepsilonsqrt{n})^{-1}$ in the leading exponential term when $varepsilonsqrt{n}$ is large.