Difference between revisions of "Fairness Without Demographics in Repeated Loss Minimization"

From statwiki
Jump to: navigation, search
Line 11: Line 11:
 
=Why Empirical Risk Minimization (ERM) does not work=
 
=Why Empirical Risk Minimization (ERM) does not work=
  
=Why Distributonally Robust Optimization (DRO) does work=
+
=Distributonally Robust Optimization (DRO)=
 +
 
 +
==Risk Bounding Over Unknown Groups==
 +
 
 +
At this point our goal is to minimize the worst-case group risk over a single time-step <math display="inline">R </math>

Revision as of 14:44, 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

Distributonally Robust Optimization (DRO)

Risk Bounding Over Unknown Groups

At this point our goal is to minimize the worst-case group risk over a single time-step [math]R [/math]