Saved in:
Bibliographic Details
Main Authors: Mele, Margherita, Moreno, Daniel Campos, Potestio, Raffaello
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.05214
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915837436231680
author Mele, Margherita
Moreno, Daniel Campos
Potestio, Raffaello
author_facet Mele, Margherita
Moreno, Daniel Campos
Potestio, Raffaello
contents Selecting the optimal resolution for discretizing high-dimensional data is a central problem in physics and data analysis, particularly in unsupervised settings where the underlying distribution is unknown. The Relevance-Resolution (Res-Rel) framework addresses this issue through an information-theoretic trade-off between descriptive detail and statistical reliability. Here we provide a systematic validation of this approach by comparing its characteristic optima--maximum relevance and the -1 slope (information-theoretic) point--with the discretization that minimizes the Kullback-Leibler divergence from a known or physically motivated ground truth distribution. Across unstructured and structured synthetic datasets, Gaussian clones of MNIST, and molecular dynamics simulations of the alanine dipeptide, we find that as the dimensionality or informative content increases the KL-optimal discretization consistently lies within the Res-Rel optimality region. Furthermore, in high-dimensional regimes the -1 slope criterion closely matches the KL divergence minimum. These results establish the quantitative consistency of unsupervised information-theoretic selection with distribution-based optimality.
format Preprint
id arxiv_https___arxiv_org_abs_2603_05214
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The bliss of dimensionality: how an unsupervised criterion identifies optimal low-resolution representations of high-dimensional datasets
Mele, Margherita
Moreno, Daniel Campos
Potestio, Raffaello
Statistical Mechanics
Selecting the optimal resolution for discretizing high-dimensional data is a central problem in physics and data analysis, particularly in unsupervised settings where the underlying distribution is unknown. The Relevance-Resolution (Res-Rel) framework addresses this issue through an information-theoretic trade-off between descriptive detail and statistical reliability. Here we provide a systematic validation of this approach by comparing its characteristic optima--maximum relevance and the -1 slope (information-theoretic) point--with the discretization that minimizes the Kullback-Leibler divergence from a known or physically motivated ground truth distribution. Across unstructured and structured synthetic datasets, Gaussian clones of MNIST, and molecular dynamics simulations of the alanine dipeptide, we find that as the dimensionality or informative content increases the KL-optimal discretization consistently lies within the Res-Rel optimality region. Furthermore, in high-dimensional regimes the -1 slope criterion closely matches the KL divergence minimum. These results establish the quantitative consistency of unsupervised information-theoretic selection with distribution-based optimality.
title The bliss of dimensionality: how an unsupervised criterion identifies optimal low-resolution representations of high-dimensional datasets
topic Statistical Mechanics
url https://arxiv.org/abs/2603.05214