Fairness Without Demographics in Repeated Loss Minimization: Difference between revisions
Jump to navigation
Jump to search
| 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} </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>. | ||
Revision as of 14:16, 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].