Taking a Moment for Distributional Robustness

arXiv:2405.05461v1 Announce Type: new
Abstract: A rich line of recent work has studied distributionally robust learning approaches that seek to learn a hypothesis that performs well, in the worst-case, on many different distributions over a population. We argue that although the most common approaches seek to minimize the worst-case loss over distributions, a more reasonable goal is to minimize the worst-case distance to the true conditional expectation of labels given each covariate. Focusing on the minmax loss objective can dramatically …

abstract arxiv case cs.lg hypothesis learn line loss moment population robust robustness seek type work