Thinning to improve two-sample discrepancy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Smirnov, Gleb, Vershynin, Roman
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911390858477568
author Smirnov, Gleb
Vershynin, Roman
author_facet Smirnov, Gleb
Vershynin, Roman
contents The discrepancy between two independent samples \(X_1,\dots,X_n\) and \(Y_1,\dots,Y_n\) drawn from the same distribution on $\mathbb{R}^d$ typically has order \(O(\sqrt{n})\) even in one dimension. We give a simple online algorithm that reduces the discrepancy to \(O(\log^{2d} n)\) by discarding a small fraction of the points.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20932
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Thinning to improve two-sample discrepancy
Smirnov, Gleb
Vershynin, Roman
Probability
Data Structures and Algorithms
The discrepancy between two independent samples \(X_1,\dots,X_n\) and \(Y_1,\dots,Y_n\) drawn from the same distribution on $\mathbb{R}^d$ typically has order \(O(\sqrt{n})\) even in one dimension. We give a simple online algorithm that reduces the discrepancy to \(O(\log^{2d} n)\) by discarding a small fraction of the points.
title Thinning to improve two-sample discrepancy
topic Probability
Data Structures and Algorithms
url https://arxiv.org/abs/2506.20932