Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.07282 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915723005132800 |
|---|---|
| author | Lang, Junjun Zhang, Qiong Liu, Yukun |
| author_facet | Lang, Junjun Zhang, Qiong Liu, Yukun |
| contents | Covariate shift arises when covariate distributions differ between source and target populations while the conditional distribution of the response remains invariant, and it underlies problems in missing data and causal inference. We propose a minimum Wasserstein distance estimation framework for inference under covariate shift that avoids explicit modeling of outcome regressions or importance weights. The resulting W-estimator admits a closed-form expression and is numerically equivalent to the classical 1-nearest neighbor estimator, yielding a new optimal transport interpretation of nearest neighbor methods. We establish root-$n$ asymptotic normality and show that the estimator is not asymptotically linear, leading to super-efficiency relative to the semiparametric efficient estimator under covariate shift in certain regimes, and uniformly in missing data problems. Numerical simulations, along with an analysis of a rainfall dataset, underscore the exceptional performance of our W-estimator. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07282 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Minimum Wasserstein distance estimator under covariate shift: closed-form, super-efficiency and irregularity Lang, Junjun Zhang, Qiong Liu, Yukun Methodology Machine Learning Covariate shift arises when covariate distributions differ between source and target populations while the conditional distribution of the response remains invariant, and it underlies problems in missing data and causal inference. We propose a minimum Wasserstein distance estimation framework for inference under covariate shift that avoids explicit modeling of outcome regressions or importance weights. The resulting W-estimator admits a closed-form expression and is numerically equivalent to the classical 1-nearest neighbor estimator, yielding a new optimal transport interpretation of nearest neighbor methods. We establish root-$n$ asymptotic normality and show that the estimator is not asymptotically linear, leading to super-efficiency relative to the semiparametric efficient estimator under covariate shift in certain regimes, and uniformly in missing data problems. Numerical simulations, along with an analysis of a rainfall dataset, underscore the exceptional performance of our W-estimator. |
| title | Minimum Wasserstein distance estimator under covariate shift: closed-form, super-efficiency and irregularity |
| topic | Methodology Machine Learning |
| url | https://arxiv.org/abs/2601.07282 |