Variable selection in maximum mean discrepancy for interpretable distribution comparison

Mitsuzawa, Kensuke; Kanagawa, Motonobu; Bortoli, Stefano; Grossi, Margherita; Papotti, Paolo
Submitted to ArXiV, 2 November 2023

Two-sample testing decides whether two datasets are generated from the same distribution. This paper studies variable selection for two-sample testing, the task being to identify the variables (or dimensions) responsible for the discrepancies between the two distributions. This task is relevant to many problems of pattern analysis and machine learning, such as dataset shift adaptation, causal inference and model validation. Our approach is based on a two-sample test based on the Maximum Mean Discrepancy (MMD). We optimise the Automatic Relevance Detection (ARD) weights defined for individual variables to maximise the power of the MMD-based test. For this optimisation, we introduce sparse regularisation and propose two methods for dealing with the issue of selecting an appropriate regularisation parameter. One method determines the regularisation parameter in a data-driven way, and the other aggregates the results of different regularisation parameters. We confirm the validity of the proposed methods by systematic comparisons with baseline methods, and demonstrate their usefulness in exploratory analysis of high-dimensional traffic simulation data. Preliminary theoretical analyses are also provided, including a rigorous definition of variable selection for two-sample testing.


Type:
Rapport
Date:
2023-11-02
Department:
Data Science
Eurecom Ref:
7482
Copyright:
© EURECOM. Personal use of this material is permitted. The definitive version of this paper was published in Submitted to ArXiV, 2 November 2023 and is available at :

PERMALINK : https://www.eurecom.fr/publication/7482