collaborators

5 papers

math.OC2025

On Rank Graduation Metrics for High Dimensional Ordinal Data

Gennaro Auricchio, Adelaide Emma Bernardelli, Paolo Giudici +1

Evaluating the reliability of machine learning classifications remains a fundamental challenge in Artificial Intelligence (AI), particularly when the target variable is multidimens…

math.AP2025

Energy distance and evolution problems: a promising tool for kinetic equations

Gennaro Auricchio, Giuseppe Toscani

We study the rate of convergence to equilibrium of the solutions to Fokker-Planck type equations with linear drift by means of Cramér and Energy distances, which have been recentl…

math-ph2025

From Kinetic Theory to AI: a Rediscovery of High-Dimensional Divergences and Their Properties

Gennaro Auricchio, Giovanni Brigati, Paolo Giudici +1

Selecting an appropriate divergence measure is a critical aspect of machine learning, as it directly impacts model performance. Among the most widely used, we find the Kullback-Lei…

math.ST2024

How to measure multidimensional variation?

Gennaro Auricchio, Paolo Giudici, Giuseppe Toscani

The coefficient of variation, which measures the variability of a distribution from its mean, is not uniquely defined in the multidimensional case, and so is the multidimensional G…

stat.ME2024

Multivariate Gini-type discrepancies

Gennaro Auricchio, Giovanni Brigati, Paolo Giudici +1

Measuring distances in a multidimensional setting is a challenging problem, which appears in many fields of science and engineering. In this paper, to measure the distance between…