Testable Learning with Distribution Shift

arXiv:2311.15142v2 Announce Type: replace-cross
Abstract: We revisit the fundamental problem of learning with distribution shift, in which a learner is given labeled samples from training distribution $D$, unlabeled samples from test distribution $D'$ and is asked to output a classifier with low test error. The standard approach in this setting is to bound the loss of a classifier in terms of some notion of distance between $D$ and $D'$. These distances, however, seem difficult to compute and do not lead …

abstract arxiv classifier cs.ds cs.lg distribution error fundamental loss low replace samples shift standard test training type