A minimax framework for quantifying risk-fairness trade-off in regression

DOI10.1214/22-AOS2198MaRDI QIDQ2091849

Evgenii Chzhen, Nicolas Schreuder

Publication date: 2 November 2022

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2007.14265

zbMATH Keywords

Pareto optimalityleast-squaresoptimal transportstatistical learningWasserstein barycenterregressionsminimax analysisalgorithmic fairnessdemographic parityrisk-fairness trade-off

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Linear regression; mixed models (62J05) Minimax procedures in statistical decision theory (62C20) Order statistics; empirical distribution functions (62G30) Foundational topics in statistics (62A99)

Uses Software

• Scikit
• conformalInference

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Distribution-Free Predictive Inference For Regression
• Optimal exponential bounds on the accuracy of classification
• A general decision theory for Huber's \(\epsilon\)-contamination model
• Optimal exponential bounds for aggregation of density estimators
• Robust linear least squares regression
• Consistent nonparametric regression. Discussion
• Robust covariance and scatter matrix estimation under Huber's contamination model
• A distribution-free theory of nonparametric regression
• Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001.
• Existence and consistency of Wasserstein barycenters
• Fairness through awareness
• Barycenters in the Wasserstein Space
• Optimal maps for the multidimensional Monge-Kantorovich problem
• Asymptotic Statistics
• Fair regression for health care spending
• The limits of distribution-free conditional predictive inference
• One-dimensional empirical measures, order statistics, and Kantorovich transport distances
• Learning Theory and Kernel Machines
• Distribution-free Prediction Bands for Non-parametric Regression
• Introduction to nonparametric estimation

This page was built for publication: A minimax framework for quantifying risk-fairness trade-off in regression