Metraipolis › archive › dc_b01d73d81bc2
Learning under Target Shift: Optimal Density Ratio Estimation and Importance-Weighted Regression — arXiv:2609.15785
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.15785
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T00:15:56.498Z
- SHA-256 of the archived text
43ef50361e3f673e2f3d51bd1f561216864406ba5440f5396c9a1e3137342618- Stable URL of this page
https://metraipolis.com/documento/dc_b01d73d81bc2
How to cite
Learning under Target Shift: Optimal Density Ratio Estimation and Importance-Weighted Regression — arXiv:2609.15785 — arXiv (en), https://arxiv.org/abs/2609.15785 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b01d73d81bc2 (Metraipolis archive dc_b01d73d81bc2, sha256 43ef50361e3f673e2f3d51bd1f561216864406ba5440f5396c9a1e3137342618)
BibTeX
@misc{dcb01d73d81bc2,
title = {Learning under Target Shift: Optimal Density Ratio Estimation and Importance-Weighted Regression — arXiv:2609.15785},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.15785},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b01d73d81bc2; sha256 43ef50361e3f673e2f3d51bd1f561216864406ba5440f5396c9a1e3137342618},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15785. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study density ratio estimation and importance-weighted regression under target shift with continuous outputs. Under target shift, the conditional distribution of the inputs given the outputs remains invariant across the training and test distributions, while the output marginal distribution may change. Although this problem has been extensively studied for discrete outputs, the continuous setting is substantially less understood: the importance weights are determined by an unknown density ratio function, for which existing estimation methods lack explicit finite-sample convergence rates. We propose a spectral regularization method in a reproducing kernel Hilbert space (RKHS) for estimating the continuous density ratio from labeled training samples and unlabeled test inputs. Under a source condition with regularity parameter $\iota>0$, we establish high-probability finite-sample guarantees and show that the estimator achieves the capacity-independent minimax-optimal RKHS-norm rate $O(n_\eta^{-\iota/(2\iota+2)})$. We then incorporate the estimated density ratio into importance-weighted regression and characterize the propagation of density-ratio estimation error to the final predictor. When sufficiently many samples are available for density ratio estimation, the resulting regression estimator attains the minimax-optimal rates of standard kernel regression. These results establish a finite-sample theory for continuous density ratio estimation and importance-weighted learning under target shift.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.15785 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T23:54:14.977Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).