Long Term Fairness for Minority Groups via Performative Distributionally Robust Optimization

Liam Peet-Pare, Nidhi Hegde, Alona Fyshe
7/12/2022
cs.LGcs.AImath.OC

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Fairness researchers in machine learning (ML) have coalesced around several fairness criteria which provide formal definitions of what it means for an ML model to be fair. However, these criteria have some serious limitations. We identify four key shortcomings of these formal fairness criteria, and aim to help to address them by extending performative prediction to include a distributionally robust objective.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Superhuman Fairness

89% match1 repo32023

How Robust is your Fair Model? Exploring the Robustness of Diverse Fairness Strategies

89% match1 repo32022

Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML

88% match2023

Developing a Philosophical Framework for Fair Machine Learning: Lessons From The Case of Algorithmic Collusion

88% match2022

Mind the Gap: A Causal Perspective on Bias Amplification in Prediction & Decision-Making

87% match2024

FairBED: A Bayesian Experimental Design Approach to Gathering Fairer Data

87% match2026

Cite this paper

@article{peetpare2022long,
  title  = {Long Term Fairness for Minority Groups via Performative Distributionally Robust Optimization},
  author = {Liam Peet-Pare and Nidhi Hegde and Alona Fyshe},
  year   = {2022},
  eprint = {2207.05777},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.05777v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.05777.svg)](https://codeofpaper.com/paper/2207.05777)

Discussion