Explaining classifiers with measures of statistical association

DOI10.1016/J.CSDA.2023.107701MaRDI QIDQ6168907zbMATH OpenFDO

Authors E. Borgonovo, Valentina Ghidini, Roman Hahn, Elmar Plischke

Publication date 11 July 2023

Published in Computational Statistics and Data Analysis (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1016/J.CSDA.2023.107701

zbMATH Keywords

explainabilitymeasures of statistical associationsensitivity measures

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08)

Recommendations

• Tractability of explaining classifier decisions
• Descriptive accuracy in explanations: the case of probabilistic classifiers
• scientific article; zbMATH DE number 7696696
• A unified logical framework for explanations in classifier systems
• Explaining black-box classifiers: properties and functions
• Non-adaptive stochastic score classification and explainable halfspace evaluation

Cites work

• A fast algorithm for computing distance correlation
• Algorithmic Learning Theory
• All models are wrong, but many are useful: learning a variable's importance by studying an entire class of prediction models simultaneously
• Ball Covariance: A Generic Measure of Dependence in Banach Space
• Brownian distance covariance
• Capturing the Intangible Concept of Information
• Controlling the false discovery rate via knockoffs
• Definitions, methods, and applications in interpretable machine learning
• Global sensitivity analysis with dependence measures
• Global sensitivity measures from given data
• scientific article; zbMATH DE number 3156743 (Why is no real title available?)
• scientific article; zbMATH DE number 3860199 (Why is no real title available?)
• Making best use of model evaluations to compute sensitivity indices
• Measurements of separation among probability densities or random variables
• Measuring and testing dependence by correlation of distances
• Measuring association with Wasserstein distances
• Mutual information for explainable deep learning of multiscale systems
• On measures of dependence
• Panning for Gold: ‘Model-X’ Knockoffs for High Dimensional Controlled Variable Selection
• Properties of Squeezed Binomial States and Squeezed Negative Binomial States
• Random forests
• RELATIONS BETWEEN TWO SETS OF VARIATES
• Sensitivity analysis based on Cramér-von Mises distance
• Statistical inference for Sobol pick-freeze Monte Carlo method
• Statistics in the big data era: failures of the machine
• Sure independence screening for ultrahigh dimensional feature space. With discussion and authors' reply
• Transformations and invariance in the sensitivity analysis of computer experiments

Cited in

(4)

• Score-Based Explanations in Data Management and Machine Learning
• Factor Importance Ranking and Selection Using Total Indices
• Differential quantile-based sensitivity in discontinuous models
• The many Shapley values for explainable artificial intelligence: a sensitivity analysis perspective

This page was built for publication: Explaining classifiers with measures of statistical association

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6168907)