Tackling algorithmic bias in neural-network classifiers using Wasserstein-2 regularization

DOI10.1007/S10851-022-01090-2MaRDI QIDQ2103876zbMATH OpenOpenAlexWikidataFDO

Authors Laurent Risser, Alberto González Sanz, Quentin Vincenot, Jean-Michel Loubes

Publication date 9 December 2022

Published in Journal of Mathematical Imaging and Vision (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1908.05783

zbMATH Keywords

regularizationimage classificationshape recognitionalgorithmic biasneural-networks

Mathematics Subject Classification ID

Computer science (68-XX) Information and communication theory, circuits (94-XX)

Recommendations

• Studying bias in visual features through the lens of optimal transport
• Wasserstein-based fairness interpretability framework for machine learning models
• Achieving fair treatment in algorithmic classification
• Certifying the fairness of KNN in the presence of dataset bias
• scientific article; zbMATH DE number 7064055

Cites work

• scientific article; zbMATH DE number 48727 (Why is no real title available?)
• scientific article; zbMATH DE number 1266748 (Why is no real title available?)
• scientific article; zbMATH DE number 1022658 (Why is no real title available?)
• scientific article; zbMATH DE number 1569102 (Why is no real title available?)
• scientific article; zbMATH DE number 1909499 (Why is no real title available?)
• scientific article; zbMATH DE number 7370636 (Why is no real title available?)
• A central limit theorem for Lp transportation cost on the real line with application to fairness assessment in machine learning
• Adaptive subgradient methods for online learning and stochastic optimization
• An algorithm for removing sensitive information: application to race-independent recidivism prediction
• Anchor Regression: Heterogeneous Data Meet Causality
• Central limit theorems for empirical transportation cost in general dimension
• Convergence of a Newton algorithm for semi-discrete optimal transport
• Empirical optimal transport on countable metric spaces: distributional limits and statistical applications
• Inference for empirical Wasserstein distances on finite spaces
• Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
• Optimization methods for large-scale machine learning

Cited in

(6)

• A comprehensive and fair comparison of two neural operators (with practical extensions) based on FAIR data
• Central limit theorems for general transportation costs
• An Improved Central Limit Theorem and Fast Convergence Rates for Entropic Transportation Costs
• Nonlinear inverse optimal transport: identifiability of the transport cost from its marginals and optimal values
• Studying bias in visual features through the lens of optimal transport
• Wasserstein-based fairness interpretability framework for machine learning models

Describes a project that uses

Uses Software

• AlexNet
• Adam
• AdaGrad
• ImageNet

This page was built for publication: Tackling algorithmic bias in neural-network classifiers using Wasserstein-2 regularization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2103876)