Statistical Guarantees for Fairness Aware Plug-In Algorithms

2021-07-27 · Drona Khurana, Srinivasan Ravichandran, Sparsh Jain, Narayanan Unny Edakunni

A plug-in algorithm to estimate Bayes Optimal Classifiers for fairness-aware binary classification has been proposed in (Menon & Williamson, 2018). However, the statistical efficacy of their approach has not been established. We prove that the plug-in algorithm is statistically consistent. We also derive finite sample guarantees associated with learning the Bayes Optimal Classifiers via the plug-in algorithm. Finally, we propose a protocol that modifies the plug-in approach, so as to simultaneously guarantee fairness and differential privacy with respect to a binary feature deemed sensitive.

📄 PDF Abstract BibTeX arXiv:2107.12783

Code (0)

등록된 구현이 없습니다.

Tasks

Binary Classification Fairness

FairRARI: A Plug and Play Framework for Fairness-Aware PageRank

2026-02-09 · Emmanouil Kariotakis, Aritra Konar arxiv

PageRank (PR) is a fundamental algorithm in graph machine learning tasks. Owing to the increasing importance of algorithmic fairness, we consider the problem of computing PR vectors subject to various group-fairness crit…

Plug-and-play dual-tree algorithm runtime analysis

2015-01-21 · Ryan R. Curtin, Dongryeol Lee, William B. March, Parikshit Ram

Numerous machine learning algorithms contain pairwise statistical problems at their core---that is, tasks that require computations over all pairs of input points if implemented naively. Often, tree structures are used t…

Density Estimation

Capuchin: Causal Database Repair for Algorithmic Fairness

2019-02-21 · Babak Salimi, Luke Rodriguez, Bill Howe, Dan Suciu

Fairness is increasingly recognized as a critical component of machine learning systems. However, it is the underlying data on which these systems are trained that often reflect discrimination, suggesting a database repa…

Fairness

Minimax Group Fairness in Strategic Classification

2024-10-03 · Emily Diana, Saeed Sharifi-Malvajerdi, Ali Vakilian

In strategic classification, agents manipulate their features, at a cost, to receive a positive classification outcome from the learner's classifier. The goal of the learner in such settings is to learn a classifier that…

Classification Fairness

Two Simple Ways to Learn Individual Fairness Metric from Data

2020-01-01 · ICML 2020 1 · Debarghya Mukherjee, Mikhail Yurochkin, Moulinath Banerjee, Yuekai Sun

Individual fairness was proposed to address some of the shortcomings of group fairness. Despite its benefits, it requires a task specific fairness metric that encodes our intuition of what is fair and what is unfair for …

BIG-bench Machine Learning Fairness Vocal Bursts Valence Prediction