Salvato in:
Dettagli Bibliografici
Autori principali: Ong, Eng-Jon, Bobrowski, Omer, Reinert, Gesine, Skraba, Primoz
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.10493
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912961159757824
author Ong, Eng-Jon
Bobrowski, Omer
Reinert, Gesine
Skraba, Primoz
author_facet Ong, Eng-Jon
Bobrowski, Omer
Reinert, Gesine
Skraba, Primoz
contents Estimating the intrinsic dimensionality (ID) of data is a fundamental problem in machine learning and computer vision, providing insight into the true degrees of freedom underlying high-dimensional observations. Existing methods often rely on geometric or distributional assumptions and can significantly fail when these assumptions are violated. In this paper, we introduce a novel ID estimator based on nearest-neighbor distance ratios that involves simple calculations and achieves state-of-the-art results. Most importantly, we provide a theoretical analysis proving that our estimator is \emph{universal}, namely, it converges to the true ID independently of the distribution generating the data. We present experimental results on benchmark manifolds and real-world datasets to demonstrate the performance of our estimator.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10493
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Universal Nearest-Neighbor Estimator for Intrinsic Dimensionality
Ong, Eng-Jon
Bobrowski, Omer
Reinert, Gesine
Skraba, Primoz
Machine Learning
Estimating the intrinsic dimensionality (ID) of data is a fundamental problem in machine learning and computer vision, providing insight into the true degrees of freedom underlying high-dimensional observations. Existing methods often rely on geometric or distributional assumptions and can significantly fail when these assumptions are violated. In this paper, we introduce a novel ID estimator based on nearest-neighbor distance ratios that involves simple calculations and achieves state-of-the-art results. Most importantly, we provide a theoretical analysis proving that our estimator is \emph{universal}, namely, it converges to the true ID independently of the distribution generating the data. We present experimental results on benchmark manifolds and real-world datasets to demonstrate the performance of our estimator.
title A Universal Nearest-Neighbor Estimator for Intrinsic Dimensionality
topic Machine Learning
url https://arxiv.org/abs/2603.10493