5 papers
Exact Functional ANOVA Decomposition for Categorical Inputs Models
Baptiste Ferrere, Nicolas Bousquet, Fabrice Gamboa +2
Functional ANOVA offers a principled framework for interpretability by decomposing a model's prediction into main effects and higher-order interactions. For independent features, t…
Generalized Functional ANOVA in Closed-Form: A Unified View of Additive Explanations
Baptiste Ferrere, Nicolas Bousquet, Fabrice Gamboa +1
The functional ANOVA, or Hoeffding decomposition, provides a principled framework for interpretability by decomposing a model prediction into main effects and higher-order interact…
WTNN: Weibull-Tailored Neural Networks for survival analysis
Gabrielle Rives, Olivier Lopez, Nicolas Bousquet
The Weibull distribution is a commonly adopted choice for modeling the survival of systems subject to maintenance over time. When only proxy indicators and censored observations ar…
Benchmarking XAI Explanations with Human-Aligned Evaluations
Rémi Kazmierczak, Steve Azzolin, Eloïse Berthier +9
We introduce PASTA (Perceptual Assessment System for explanaTion of Artificial Intelligence), a novel human-centric framework for evaluating eXplainable AI (XAI) techniques in comp…
Fisher-Rao distance between truncated distributions and robustness analysis in uncertainty quantification
Baalu Belay Ketema, Nicolas Bousquet, Francesco Costantino +3
Input variables in numerical models are often subject to several levels of uncertainty, usually modeled by probability distributions. In the context of uncertainty quantification a…