English
Related papers

Related papers: On consistent estimation of dimension values

200 papers

We consider a sequence of identically independently distributed random samples from an absolutely continuous probability measure in one dimension with unbounded density. We establish a new rate of convergence of the $\infty-$Wasserstein…

Probability · Mathematics 2018-08-03 Anning Liu , Jian-Guo Liu , Yulong Lu

For a given metric measure space $(X,d,\mu)$ we consider finite samples of points, calculate the matrix of distances between them and then reconstruct the points in some finite-dimensional space using the multidimensional scaling (MDS)…

Metric Geometry · Mathematics 2022-08-02 Alexey Kroshnin , Eugene Stepanov , Dario Trevisan

We give concentration inequalities in Wasserstein distance for the empirical measure of a sequence of independent and identically distributed random variables with values in a Polish space E. These inequalities involve the covering…

Probability · Mathematics 2026-01-19 Jérôme Dedecker , Aurélie Fischer , Bertrand Michel

It is easy to show that the lower and the upper box dimensions of a bounded set in Euclidean space are invariant with respect to the ambient space. In this article we show that the Minkowski content of a Minkowski measurable set is also…

Metric Geometry · Mathematics 2015-06-05 Maja Resman

After calculating the Dushnik-Miller dimension of Minkowski spaces to be countable infinity, we define a novel notion of dimension for ordered spaces recovering the correct manifold dimension and obtain a corresponding obstruction for the…

Metric Geometry · Mathematics 2024-03-08 Olaf Müller

We propose an axiomatic approach to the concept of an intrinsic dimension of a dataset, based on a viewpoint of geometry of high-dimensional structures. Our first axiom postulates that high values of dimension be indicative of the presence…

Machine Learning · Computer Science 2016-11-17 Vladimir Pestov

The purpose of this article is to introduce and motivate the notion of Minkowski (or box) dimension for measures. The definition is simple and fills a gap in the existing literature on the dimension theory of measures. As the terminology…

Classical Analysis and ODEs · Mathematics 2024-03-20 Kenneth J. Falconer , Jonathan M. Fraser , Antti Käenmäki

This paper introduces a natural definition for the volume of the unit ball in $n$-dimensional normed spaces $\mathbb{R}^n$. This definition preserves the Euclidean relation $P(B)/V(B)=n$ between the perimiter and the volume of the unit ball…

Metric Geometry · Mathematics 2026-05-05 Gershon Wolansky

Motivated by the manifold hypothesis, which states that data with a high extrinsic dimension may yet have a low intrinsic dimension, we develop refined statistical bounds for entropic optimal transport that are sensitive to the intrinsic…

Statistics Theory · Mathematics 2023-08-25 Austin J. Stromme

Magnitude is a numerical invariant of compact metric spaces, originally inspired by category theory and now known to be related to myriad other geometric quantities. Generalizing earlier results in $\ell_1^n$ and Euclidean space, we prove…

Metric Geometry · Mathematics 2023-11-30 Mark W. Meckes

We prove that an approximated version of the Brunn--Minkowski inequality with volume distortion coefficient implies a Gaussian concentration-of-measure phenomenon. Our main theorem is applicable to discrete spaces.

Differential Geometry · Mathematics 2008-05-08 Masayoshi Watanabe

The r-parallel set to a set A in a Euclidean space consists of all points with distance at most r from A. We clarify the relation between the volume and the surface area of parallel sets and study the asymptotic behaviour of both quantities…

Classical Analysis and ODEs · Mathematics 2011-11-09 Jan Rataj , Steffen Winter

The magnitude of a metric space is a novel invariant that provides a measure of the 'effective size' of a space across multiple scales, while also capturing numerous geometrical properties, such as curvature, density, or entropy. We develop…

Machine Learning · Computer Science 2025-01-16 Katharina Limbeck , Rayna Andreeva , Rik Sarkar , Bastian Rieck

Information about intrinsic dimension is crucial to perform dimensionality reduction, compress information, design efficient algorithms, and do statistical adaptation. In this paper we propose an estimator for the intrinsic dimension of a…

Machine Learning · Statistics 2017-11-09 Paulo Serra , Michel Mandjes

It is a classical fact, that given an arbitrary n-dimensional convex body, there exists an appropriate sequence of Minkowski symmetrizations (or Steiner symmetrizations), that converges in Hausdorff metric to a Euclidean ball. Here we…

Metric Geometry · Mathematics 2007-05-23 B. Klartag

We consider fixed-point equations for probability measures charging measured compact metric spaces that naturally yield continuum random trees. On the one hand, we study the existence/uniqueness of the fixed-points and the convergence of…

Probability · Mathematics 2021-05-05 Nicolas Broutin , Henning Sulzbach

In statistics, independent, identically distributed random samples do not carry a natural ordering, and their statistics are typically invariant with respect to permutations of their order. Thus, an $n$-sample in a space $M$ can be…

Statistics Theory · Mathematics 2023-12-08 Philipp Harms , Peter W. Michor , Xavier Pennec , Stefan Sommer

Let $S$ be a finite set, and $X_1,\ldots,X_n$ an i.i.d. uniform sample from $S$. To estimate the size $|S|$, without further structure, one can wait for repeats and use the birthday problem. This requires a sample size of the order…

Statistics Theory · Mathematics 2026-04-28 Sourav Chatterjee , Persi Diaconis , Susan Holmes

An important theme in modern inverse problems is the reconstruction of time-dependent data from only finitely many measurements. To obtain satisfactory reconstruction results in this setting it is essential to strongly exploit temporal…

Numerical Analysis · Mathematics 2024-03-14 Martin Holler , Alexander Schlüter , Benedikt Wirth

The concepts of spread and spread dimension of a metric space were introduced by Willerton in the context of quantifying biodiversity of ecosystems. This paper develops practical applications of spread dimension in the context of machine…

Metric Geometry · Mathematics 2023-08-04 Kevin Dunne