all AI news
Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization. (arXiv:2202.06856v2 [cs.LG] UPDATED)
Oct. 31, 2022, 1:12 a.m. | Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski
cs.LG updates on arXiv.org arxiv.org
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 …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
DevOps Engineer (Data Team)
@ Reward Gateway | Sofia/Plovdiv