2022 Intrinsic dimension of geometric data sets
Tom Hanika, Friedrich Martin Schneider, Gerd Stumme
Tohoku Math. J. (2) 74(1): 23-52 (2022). DOI: 10.2748/tmj.20201015a


The curse of dimensionality is a phenomenon frequently observed in machine learning (ML) and knowledge discovery (KD). There is a large body of literature investigating its origin and impact, using methods from mathematics as well as from computer science. Among the mathematical insights into data dimensionality, there is an intimate link between the dimension curse and the phenomenon of measure concentration, which makes the former accessible to methods of geometric analysis. The present work provides a comprehensive study of the intrinsic geometry of a data set, based on Gromov's metric measure geometry and Pestov's axiomatic approach to intrinsic dimension. In detail, we define a concept of geometric data set and introduce a metric as well as a partial order on the set of isomorphism classes of such data sets. Based on these objects, we propose and investigate an axiomatic approach to the intrinsic dimension of geometric data sets and establish a concrete dimension function with the desired properties. Our model for data sets and their intrinsic dimension is computationally feasible and, moreover, adaptable to specific ML/KD-algorithms, as illustrated by various experiments.


Download Citation

Tom Hanika. Friedrich Martin Schneider. Gerd Stumme. "Intrinsic dimension of geometric data sets." Tohoku Math. J. (2) 74 (1) 23 - 52, 2022. https://doi.org/10.2748/tmj.20201015a


Published: 2022
First available in Project Euclid: 27 January 2022

Digital Object Identifier: 10.2748/tmj.20201015a

Primary: 53C23
Secondary: 51F99 , 68P05 , 68T01

Keywords: dimension curse , intrinsic dimension , lattices , metric measure space , observable diameter

Rights: Copyright © 2022 Tohoku University


This article is only available to subscribers.
It is not available for individual sale.

Vol.74 • No. 1 • 2022
Back to Top