Fairness Without Demographics in Repeated Loss Minimization: Difference between revisions

From statwiki
Jump to navigation Jump to search
No edit summary
Line 15: Line 15:
==Risk Bounding Over Unknown Groups==
==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">\mathcal{R}_{max} (\theta^{(t)}) </math>. As previously mentioned, this is difficult to do because neither the population proportions <math display="inline">\{a_k\} </math> nor group distributions <math display="inline">\{P_k\} </math> are known. Therefore, Hashimoto et al. developed an optimization technique that is robust "against '''''all''''' directions around the data generating distribution". This refers to fact that this distributionally robust optimization (DRO) is robust to any group distribution <math display="inline">\{P_k\} </math> if the population proportion <math display="inline">\{a_k\} </math> is greater than or equal to the lowest population proportion <math display="inline">a_{min} </math>.
At this point our goal is to minimize the worst-case group risk over a single time-step <math display="inline">\mathcal{R}_{max} (\theta^{(t)}) </math>. As previously mentioned, this is difficult to do because neither the population proportions <math display="inline">\{a_k\} </math> nor group distributions <math display="inline">\{P_k\} </math> are known. Therefore, Hashimoto et al. developed an optimization technique that is robust "against '''''all''''' directions around the data generating distribution". This refers to fact that this distributionally robust optimization (DRO) is robust to any group distribution <math display="inline">P_k </math> of a Group <math display="inline">k \in K</math> if the population proportion <math display="inline">a_k </math> of this group is greater than or equal to the lowest population proportion <math display="inline">a_{min} </math> (which is specified in practice).

Revision as of 15:45, 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]\displaystyle{ \mathcal{R}_{max} (\theta^{(t)}) }[/math]. As previously mentioned, this is difficult to do because neither the population proportions [math]\displaystyle{ \{a_k\} }[/math] nor group distributions [math]\displaystyle{ \{P_k\} }[/math] are known. Therefore, Hashimoto et al. developed an optimization technique that is robust "against all directions around the data generating distribution". This refers to fact that this distributionally robust optimization (DRO) is robust to any group distribution [math]\displaystyle{ P_k }[/math] of a Group [math]\displaystyle{ k \in K }[/math] if the population proportion [math]\displaystyle{ a_k }[/math] of this group is greater than or equal to the lowest population proportion [math]\displaystyle{ a_{min} }[/math] (which is specified in practice).