@inproceedings{76be94513da64c57aad4230caa1e1e75,
title = "Near-Optimal Linear Regression under Distribution Shift",
abstract = "Transfer learning is essential when sufficient data comes from the source domain, with scarce labeled data from the target domain. We develop estimators that achieve minimax linear risk for linear regression problems under distribution shift. Our algorithms cover different transfer learning settings including covariate shift and model shift. We also consider when data are generated from either linear or general nonlinear models. We show that linear minimax estimators are within an absolute constant of the minimax risk even among nonlinear estimators for various source/target distributions.",
author = "Qi Lei and Wei Hu and Lee, {Jason D.}",
note = "Funding Information: QL was supported by NSF #2030859 and the Computing Research Association for the CIFellows Project. WH was supported by NSF, ONR, Simons Foundation, Schmidt Foundation, Amazon Research, DARPA and SRC. JDL was supported by ARO under MURI Award W911NF-11-1-0303, the Sloan Research Fellowship, and NSF CCF 2002272. Publisher Copyright: Copyright {\textcopyright} 2021 by the author(s); 38th International Conference on Machine Learning, ICML 2021 ; Conference date: 18-07-2021 Through 24-07-2021",
year = "2021",
language = "English (US)",
series = "Proceedings of Machine Learning Research",
publisher = "ML Research Press",
pages = "6164--6174",
booktitle = "Proceedings of the 38th International Conference on Machine Learning, ICML 2021",
}