Fairness Without Demographics in Repeated Loss Minimization: Difference between revisions
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>. | 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>. | ||
Revision as of 14:41, 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] if the population proportion [math]\displaystyle{ \{a_k\} }[/math] is greater than or equal to the lowest population proportion [math]\displaystyle{ a_{min} }[/math].