Skip to yearly menu bar Skip to main content


Poster

Simple and near-optimal algorithms for hidden stratification and multi-group learning

Christopher Tosh · Daniel Hsu

Hall E #1215

Keywords: [ T: Domain Adaptation and Transfer Learning ] [ T: Learning Theory ] [ Theory ]


Abstract:

Multi-group agnostic learning is a formal learning criterion that is concerned with the conditional risks of predictors within subgroups of a population. The criterion addresses recent practical concerns such as subgroup fairness and hidden stratification. This paper studies the structure of solutions to the multi-group learningproblem, and provides simple and near-optimal algorithms for the learning problem.

Chat is not available.