Using Property Elicitation to Understand the Impacts of Fairness Regularizers

Predictive algorithms are often trained by optimizing some loss function, to which regularization functions are added to impose a penalty for violating constraints. As expected, the addition of such regularization functions can change the minimizer of the objective. It is not well-understood which r...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Author Finocchiaro, Jessie
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 18.12.2023
Subjects
Algorithms
Machine learning
Optimization
Regularization
Online AccessGet full text

Cover

More Information
Summary:Predictive algorithms are often trained by optimizing some loss function, to which regularization functions are added to impose a penalty for violating constraints. As expected, the addition of such regularization functions can change the minimizer of the objective. It is not well-understood which regularizers change the minimizer of the loss, and, when the minimizer does change, how it changes. We use property elicitation to take first steps towards understanding the joint relationship between the loss and regularization functions and the optimal decision for a given problem instance. In particular, we give a necessary and sufficient condition on loss and regularizer pairs for when a property changes with the addition of the regularizer, and examine some regularizers satisfying this condition standard in the fair machine learning literature. We empirically demonstrate how algorithmic decision-making changes as a function of both data distribution changes and hardness of the constraints.
ISSN:2331-8422