1 citations · 4 across the 8 of their papers we have counts for
8 papers
Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models
Marouane Il Idrissi, Agathe Fernandes Machado, Arthur Charpentier
Cooperative game theory has become a cornerstone of post-hoc interpretability in machine learning, largely through the use of Shapley values. Yet, despite their widespread adoption…
Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervals
Marouane Il Idrissi, Agathe Fernandes Machado, Ewen Gallic +1
Cooperative game theory methods, notably Shapley values, have significantly enhanced machine learning (ML) interpretability. However, existing explainable AI (XAI) frameworks mainl…
Hoeffding decomposition of black-box models with dependent inputs
Marouane Il Idrissi, Nicolas Bousquet, Fabrice Gamboa +2
Performing an additive decomposition of arbitrary functions of random elements is paramount for global sensitivity analysis and, therefore, the interpretation of black-box models.…
Shapley effects and proportional marginal effects for global sensitivity analysis: application to computed tomography scan organ dose estimation
Anais Foucault, Marouane Il Idrissi, Bertrand Iooss +1
Concerns have been raised about possible cancer risks after exposure to computed tomography (CT) scans in childhood. The health effects of ionizing radiation are then estimated fro…
On the coalitional decomposition of parameters of interest
Marouane Il Idrissi, Nicolas Bousquet, Fabrice Gamboa +2
Understanding the behavior of a black-box model with probabilistic inputs can be based on the decomposition of a parameter of interest (e.g., its variance) into contributions attri…
Proportional marginal effects for global sensitivity analysis
Margot Herin, Marouane Il Idrissi, Vincent Chabridon +1
Performing (variance-based) global sensitivity analysis (GSA) with dependent inputs has recently benefited from cooperative game theory concepts.By using this theory, despite the p…
Quantile-constrained Wasserstein projections for robust interpretability of numerical and machine learning models
Marouane Il Idrissi, Nicolas Bousquet, Fabrice Gamboa +2
Robustness studies of black-box models is recognized as a necessary task for numerical models based on structural equations and predictive models learned from data. These studies m…
Developments and applications of Shapley effects to reliability-oriented sensitivity analysis with correlated inputs
Marouane Il Idrissi, Vincent Chabridon, Bertrand Iooss
Reliability-oriented sensitivity analysis methods have been developed for understanding the influence of model inputs relative to events which characterize the failure of a system…