Distribution-Free Statistical Dispersion Control for Societal Applications

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Deng, Zhun, Zollo, Thomas P., Snell, Jake C., Pitassi, Toniann, Zemel, Richard
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917605320687616
author Deng, Zhun
Zollo, Thomas P.
Snell, Jake C.
Pitassi, Toniann
Zemel, Richard
author_facet Deng, Zhun
Zollo, Thomas P.
Snell, Jake C.
Pitassi, Toniann
Zemel, Richard
contents Explicit finite-sample statistical guarantees on model performance are an important ingredient in responsible machine learning. Previous work has focused mainly on bounding either the expected loss of a predictor or the probability that an individual prediction will incur a loss value in a specified range. However, for many high-stakes applications, it is crucial to understand and control the dispersion of a loss distribution, or the extent to which different members of a population experience unequal effects of algorithmic decisions. We initiate the study of distribution-free control of statistical dispersion measures with societal implications and propose a simple yet flexible framework that allows us to handle a much richer class of statistical functionals beyond previous work. Our methods are verified through experiments in toxic comment detection, medical imaging, and film recommendation.
format Preprint
id arxiv_https___arxiv_org_abs_2309_13786
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Distribution-Free Statistical Dispersion Control for Societal Applications
Deng, Zhun
Zollo, Thomas P.
Snell, Jake C.
Pitassi, Toniann
Zemel, Richard
Machine Learning
Explicit finite-sample statistical guarantees on model performance are an important ingredient in responsible machine learning. Previous work has focused mainly on bounding either the expected loss of a predictor or the probability that an individual prediction will incur a loss value in a specified range. However, for many high-stakes applications, it is crucial to understand and control the dispersion of a loss distribution, or the extent to which different members of a population experience unequal effects of algorithmic decisions. We initiate the study of distribution-free control of statistical dispersion measures with societal implications and propose a simple yet flexible framework that allows us to handle a much richer class of statistical functionals beyond previous work. Our methods are verified through experiments in toxic comment detection, medical imaging, and film recommendation.
title Distribution-Free Statistical Dispersion Control for Societal Applications
topic Machine Learning
url https://arxiv.org/abs/2309.13786