zeyut_ms_phil_2021_R.pdf (1.04 MB)
Download file

Think Twice Before Enforcing A Notion: A Reflection and a Case Study on Fairness in Machine Learning

Download (1.04 MB)
thesis
posted on 07.12.2021, 18:37 authored by figshare admin cmufigshare admin cmu
The thesis presents a reflection and a case study of fairness notions in machine learning. I review commonly used fairness notions and reflect on the subtleties with respect to the role played by causality in fairness analysis. Then focusing on the Equalized Odds notion of fairness, I consider the theoretical attainability of Equalized Odds and, furthermore, if it is attainable, the optimality of the prediction performance under various settings. In particular, for prediction performed by a deterministic function of input features, I give the conditions under which Equalized Odds can hold true; if the stochastic prediction is acceptable, I show that under mild assumptions, fair predictors can always be derived. For classification tasks, I further prove that compared to enforcing fairness by post-processing, one can further benefit from exploiting all available features during training and get potentially better prediction performance while remaining fair.

History

Date

27/08/2021

Degree Type

Master's Thesis

Department

Philosophy

Degree Name

  • Master of Science (MS)

Advisor(s)

Kun Zhang

Usage metrics

Categories

Licence

Exports