Fairness Without Demographics in Repeated Loss Minimization: Difference between revisions

From statwiki
Jump to navigation Jump to search
No edit summary
No edit summary
Line 9: Line 9:
=Example and Problem Setup=
=Example and Problem Setup=


=Disparity Amplification=
=Why Empirical Risk Minimization (ERM) does not work=
 
=Why Distributonally Robust Optimization (DRO) does work=

Revision as of 14:18, 19 October 2018

This page contains the summary of the paper "Fairness Without Demographics in Repeated Loss Minimization" by Hashimoto, T. B., Srivastava, M., Namkoong, H., & Liang, P. which was published at the International Conference of Machine Learning (ICML) in 2018. In the following, an

Overview of the Paper

Introduction

Fairness

Example and Problem Setup

Why Empirical Risk Minimization (ERM) does not work

Why Distributonally Robust Optimization (DRO) does work