Explaining machine learning models using entropic variable projection

DOI10.1093/IMAIAI/IAAD010MaRDI QIDQ6548431zbMATH OpenFDO

Authors François Bachoc, Fabrice Gamboa, Max Halford, Jean-Michel Loubes, Laurent Risser

Publication date 1 June 2024

Published in Information and Inference: A Journal of the IMA (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1093/IMAIAI/IAAD010

zbMATH Keywords

black-Box decision rulesexplainabilityKullback-Leibler divergenceWasserstein distance

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Recommendations

• How to explain individual classification decisions
• An efficient explanation of individual classifications using game theory
• The explanation game: a formal framework for interpretable machine learning
• Foundations of fine-grained explainability
• Explaining individual predictions when features are dependent: more accurate approximations to Shapley values

Cited in

(4)

• Reduction of the shallow water system by an error aware POD-neural network method: application to floodplain dynamics
• Quantile-constrained Wasserstein projections for robust interpretability of numerical and machine learning models
• Fisher-Rao distance between truncated distributions and robustness analysis in uncertainty quantification
• Contribution of subsets of variables in global sensitivity analysis with dependent variables

This page was built for publication: Explaining machine learning models using entropic variable projection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6548431)