FAIRM: Learning invariant representations for algorithmic fairness and domain generalization with minimax optimality

arXiv:2404.01608v1 Announce Type: cross
Abstract: Machine learning methods often assume that the test data have the same distribution as the training data. However, this assumption may not hold due to multiple levels of heterogeneity in applications, raising issues in algorithmic fairness and domain generalization. In this work, we address the problem of fair and generalizable machine learning by invariant principles. We propose a training environment-based oracle, FAIRM, which has desirable fairness and domain generalization properties under a diversity-type condition. We …

abstract algorithmic fairness applications arxiv cs.lg data distribution domain fairness however machine machine learning minimax multiple stat.me stat.ml test training training data type work