Learning Non-Discriminatory Predictors

2017-02-20 · Blake Woodworth, Suriya Gunasekar, Mesrob I. Ohannessian, Nathan Srebro

We consider learning a predictor which is non-discriminatory with respect to a "protected attribute" according to the notion of "equalized odds" proposed by Hardt et al. [2016]. We study the problem of learning such a non-discriminatory predictor from a finite training set, both statistically and computationally. We show that a post-hoc correction approach, as suggested by Hardt et al, can be highly suboptimal, present a nearly-optimal statistical procedure, argue that the associated computational problem is intractable, and suggest a second moment relaxation of the non-discrimination definition for which learning is tractable.

📄 PDF Abstract BibTeX arXiv:1702.06081

Code (0)

등록된 구현이 없습니다.

Tasks

Attribute

Fair Learning with Private Demographic Data

2020-02-26 · ICML 2020 1 · Hussein Mozannar, Mesrob I. Ohannessian, Nathan Srebro

Sensitive attributes such as race are rarely available to learners in real world settings as their collection is often restricted by laws and regulations. We give a scheme that allows individuals to release their sensiti…

Equal Opportunity and Affirmative Action via Counterfactual Predictions

2019-05-26 · Yixin Wang, Dhanya Sridhar, David M. Blei

Machine learning (ML) can automate decision-making by learning to predict decisions from historical data. However, these predictors may inherit discriminatory policies from past decisions and reproduce unfair decisions. …

counterfactual Decision Making Fairness

A Shapley Value Solution to Game Theoretic-based Feature Reduction in False Alarm Detection

2015-12-05 · Fatemeh Afghah, Abolfazl Razi, Kayvan Najarian

False alarm is one of the main concerns in intensive care units and can result in care disruption, sleep deprivation, and insensitivity of care-givers to alarms. Several methods have been proposed to suppress the false a…

General Classification

Fairness in Supervised Learning: An Information Theoretic Approach

2018-01-13 · AmirEmad Ghassami, Sajad Khodadadian, Negar Kiyavash

Automated decision making systems are increasingly being used in real-world applications. In these systems for the most part, the decision rules are derived by minimizing the training error on the available historical da…

Attribute Decision Making Fairness

Counterfactual Fairness

2017-03-20 · NeurIPS 2017 12 · Matt J. Kusner, Joshua R. Loftus, Chris Russell, Ricardo Silva

Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, previous decis…

BIG-bench Machine Learning Causal Inference counterfactual Fairness