Improving Out-of-Distribution Robustness via Selective Augmentation. (arXiv:2201.00299v1 [cs.LG])

Machine learning algorithms typically assume that training and test examples
are drawn from the same distribution. However, distribution shift is a common
problem in real-world applications and can cause models to perform dramatically
worse at test time. In this paper, we specifically consider the problems of
domain shifts and subpopulation shifts (eg. imbalanced data). While prior works
often seek to explicitly regularize internal representations and predictors of
the model to be domain invariant, we instead aim to regularize the whole …

arxiv augmentation distribution