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 ]
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.