Hoeffding decomposition of black-box models with dependent inputs - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Hoeffding decomposition of black-box models with dependent inputs

Résumé

One of the main challenges for interpreting black-box models is the ability to uniquely decompose square-integrable functions of non-independent random inputs into a sum of functions of every possible subset of variables. However, dealing with dependencies among inputs can be complicated. We propose a novel framework to study this problem, linking three domains of mathematics: probability theory, functional analysis, and combinatorics. We show that, under two reasonable assumptions on the inputs (non-perfect functional dependence and non-degenerate stochastic dependence), it is always possible to decompose such a function uniquely. This generalizes the well-known Hoeffding decomposition. The elements of this decomposition can be expressed using oblique projections and allow for novel interpretability indices for evaluation and variance decomposition purposes. The properties of these novel indices are studied and discussed. This generalization offers a path towards a more precise uncertainty quantification, which can benefit sensitivity analysis and interpretability studies whenever the inputs are dependent. This decomposition is illustrated analytically, and the challenges for adopting these results in practice are discussed.
Fichier principal
Vignette du fichier
GenAnova-preprint.pdf (391.24 Ko) Télécharger le fichier

Dates et versions

hal-04233915 , version 1 (09-10-2023)
hal-04233915 , version 2 (07-03-2024)

Identifiants

Citer

Marouane Il Idrissi, Nicolas Bousquet, Fabrice Gamboa, Bertrand Iooss, Jean-Michel Loubes. Hoeffding decomposition of black-box models with dependent inputs. 2024. ⟨hal-04233915v2⟩
132 Consultations
45 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More