Nearest-Neighbor Radii under Dependent Sampling

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gao, Yuanyuan, Hou, Yilong, Lin, Zhexiao
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911684105338880
author Gao, Yuanyuan
Hou, Yilong
Lin, Zhexiao
author_facet Gao, Yuanyuan
Hou, Yilong
Lin, Zhexiao
contents Nearest-neighbor methods are fundamental to classical and modern machine learning, yet their geometric properties are typically analyzed under independent sampling. In this paper, we study the nearest-neighbor radii under dependent sampling. We consider strong mixing dependent observations and ask whether dependence changes the scale of nearest-neighbor neighborhoods. We establish distribution-free almost sure convergence under polynomial mixing and sharp non-asymptotic moment bounds under geometric mixing. The moment bounds depend on the local intrinsic dimension rather than the ambient dimension, making the results applicable to high-dimensional data concentrated near lower-dimensional manifolds. Synthetic experiments and real-world time-series benchmarks support the theory, showing that nearest-neighbor geometry remains informative under dependence sampling.
format Preprint
id arxiv_https___arxiv_org_abs_2605_14343
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Nearest-Neighbor Radii under Dependent Sampling
Gao, Yuanyuan
Hou, Yilong
Lin, Zhexiao
Machine Learning
Statistics Theory
Nearest-neighbor methods are fundamental to classical and modern machine learning, yet their geometric properties are typically analyzed under independent sampling. In this paper, we study the nearest-neighbor radii under dependent sampling. We consider strong mixing dependent observations and ask whether dependence changes the scale of nearest-neighbor neighborhoods. We establish distribution-free almost sure convergence under polynomial mixing and sharp non-asymptotic moment bounds under geometric mixing. The moment bounds depend on the local intrinsic dimension rather than the ambient dimension, making the results applicable to high-dimensional data concentrated near lower-dimensional manifolds. Synthetic experiments and real-world time-series benchmarks support the theory, showing that nearest-neighbor geometry remains informative under dependence sampling.
title Nearest-Neighbor Radii under Dependent Sampling
topic Machine Learning
Statistics Theory
url https://arxiv.org/abs/2605.14343