Distributionally Robust Losses for Latent Covariate Mixtures. (arXiv:2007.13982v2 [cs.LG] UPDATED)

While modern large-scale datasets often consist of heterogeneous
subpopulations -- for example, multiple demographic groups or multiple text
corpora -- the standard practice of minimizing average loss fails to guarantee
uniformly low losses across all subpopulations. We propose a convex procedure
that controls the worst-case performance over all subpopulations of a given
size. Our procedure comes with finite-sample (nonparametric) convergence
guarantees on the worst-off subpopulation. Empirically, we observe on lexical
similarity, wine quality, and recidivism prediction tasks that our worst-case …

arxiv lg losses