Minimax Regret Learning for Data with Heterogeneous Subgroups

arXiv:2405.01709v1 Announce Type: cross
Abstract: Modern complex datasets often consist of various sub-populations. To develop robust and generalizable methods in the presence of sub-population heterogeneity, it is important to guarantee a uniform learning performance instead of an average one. In many applications, prior information is often available on which sub-population or group the data points belong to. Given the observed groups of data, we develop a min-max-regret (MMR) learning framework for general supervised learning, which targets to minimize the worst-group …

abstract applications arxiv data datasets information math.st minimax modern performance population prior robust stat.me stat.ml stat.th subgroups type uniform