Understanding black-box models with dependent inputs through a generalization of Hoeffding’s decomposition - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Understanding black-box models with dependent inputs through a generalization of Hoeffding’s decomposition

Résumé

One of the main challenges for interpreting black-box models is the ability to uniquely decompose square-integrable functions of non-mutually 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 uniquely such a function. This ``canonical decomposition'' is relatively intuitive and unveils the linear nature of non-linear functions of non-linearly dependent inputs. In this framework, we effectively generalize the well-known Hoeffding decomposition, which can be seen as a particular case. Oblique projections of the black-box model allow for novel interpretability indices for evaluation and variance decomposition. Aside from their intuitive nature, the properties of these novel indices are studied and discussed. This result offers a path towards a more precise uncertainty quantification, which can benefit sensitivity analyses and interpretability studies, whenever the inputs are dependent. This decomposition is illustrated analytically, and the challenges to adopting these results in practice are discussed.
Fichier principal
Vignette du fichier
GenAnova-preprint.pdf (417.18 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

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. Understanding black-box models with dependent inputs through a generalization of Hoeffding’s decomposition. 2023. ⟨hal-04233915v1⟩
142 Consultations
82 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More