In partially identified linear models, the worst-case robust risk yields a minimax predictor that abstains on unseen shift directions and provably outperforms anchor regression and OLS when test shifts include new directions.
Partial transportability for domain generalization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Achievable distributional robustness when the robust risk is only partially identified
In partially identified linear models, the worst-case robust risk yields a minimax predictor that abstains on unseen shift directions and provably outperforms anchor regression and OLS when test shifts include new directions.