English

Glivenko-Cantelli for $f$-divergence

Statistics Theory 2025-03-25 v2 Machine Learning Statistics Theory

Abstract

We extend the celebrated Glivenko-Cantelli theorem, sometimes called the fundamental theorem of statistics, from its standard setting of total variation distance to all ff-divergences. A key obstacle in this endeavor is to define ff-divergence on a subcollection of a σ\sigma-algebra that forms a π\pi-system but not a σ\sigma-subalgebra. This is a side contribution of our work. We will show that this notion of ff-divergence on the π\pi-system of rays preserves nearly all known properties of standard ff-divergence, yields a novel integral representation of the Kolmogorov-Smirnov distance, and has a Glivenko-Cantelli theorem. We will also discuss the prospects of a Vapnik-Chervonenkis theory for ff-divergence.

Keywords

Cite

@article{arxiv.2503.17355,
  title  = {Glivenko-Cantelli for $f$-divergence},
  author = {Haoming Wang and Lek-Heng Lim},
  journal= {arXiv preprint arXiv:2503.17355},
  year   = {2025}
}

Comments

26 pages, 1 figure

R2 v1 2026-06-28T22:30:08.291Z