Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization. (arXiv:2202.06856v2 [cs.LG] UPDATED)

A common explanation for the failure of deep networks to generalize
out-of-distribution is that they fail to recover the "correct" features. We
challenge this notion with a simple experiment which suggests that ERM already
learns sufficient features and that the current bottleneck is not feature
learning, but robust regression. Our findings also imply that given a small
amount of data from the target distribution, retraining only the last linear
layer will give excellent performance. We therefore argue that devising simpler …

arxiv distribution erm features learn regression