Abstract:This paper studies nonparametric regression with repeated measurements when the response in the target domain is unobservable or costly to collect. We adopt a transfer learning framework that leverages a source domain with observable responses under covariate shift. The target regression function is estimated by correcting the distribution shift via the density ratio. We consider both known and unknown density ratio scenarios, which reflect different data available for nonparametric regression estimation. In both cases, we further address two settings: the uniformly bounded density ratio and the unbounded case with finite moment conditions. Under the unknown density ratio scenario, both the density ratio and the target regression function are estimated using rectified linear unit (ReLU) feedforward neural networks (FNNs), whereas under the known density ratio scenario, only the target regression function is estimated by ReLU FNNs. Theoretically, we establish non-asymptotic error bounds for the proposed estimators and prove that they achieve the minimax optimal convergence rate under the repeated measurements setting. Notably, we develop a novel approximation theory where the constants of the network parameters depend polynomially, rather than exponentially as in existing works, on the dimension, thereby mitigating the curse of dimensionality. Consequently, we derive sharper non-asymptotic bounds for the stochastic error. The finite sample performance of the proposed method is demonstrated through numerical simulations and a real data application.
| Comments: | 59 pages, 2 figures, 2 tables, including appendix |
| Subjects: | Methodology (stat.ME) |
| MSC classes: | 62G08 |
| Cite as: | arXiv:2605.24854 [stat.ME] |
| (or arXiv:2605.24854v1 [stat.ME] for this version) | |
| https://doi.org/10.48550/arXiv.2605.24854 arXiv-issued DOI via DataCite (pending registration) |
From: Yingxuan Wang [view email]
[v1]
Sun, 24 May 2026 04:17:14 UTC (737 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。