Metraipolis › archive › dc_2cc34223da76

Transfer Learning in Nonparametric Regression with Deep ReLU Networks — arXiv:2608.20255

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20255
License (as archived)
CC0-1.0
Archived
2026-10-18T11:48:50.548Z
SHA-256 of the archived text
9f5476b19829eff6e2d2e6bad263713e3c05c14f9a3172e94d2ac56b666c7312
Stable URL of this page
https://metraipolis.com/documento/dc_2cc34223da76

How to cite

Transfer Learning in Nonparametric Regression with Deep ReLU Networks — arXiv:2608.20255 — arXiv (en), https://arxiv.org/abs/2608.20255 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2cc34223da76 (Metraipolis archive dc_2cc34223da76, sha256 9f5476b19829eff6e2d2e6bad263713e3c05c14f9a3172e94d2ac56b666c7312)
BibTeX
@misc{dc2cc34223da76,
  title = {Transfer Learning in Nonparametric Regression with Deep ReLU Networks — arXiv:2608.20255},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20255},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2cc34223da76; sha256 9f5476b19829eff6e2d2e6bad263713e3c05c14f9a3172e94d2ac56b666c7312},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20255. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper develops a general transfer learning framework for nonparametric regression with data consisting of multiple groups. Under the assumption that groups share a common structure along with group-specific deviations in additive form, the proposed method employs a two-stage offset learning procedure: the first stage pools data from all groups to estimate an overall mean function, and the second stage estimates offsets for each group, yielding final group-level estimators through additive combination. Upper bounds on the $\mathcal L_2$ error are established for the proposed framework, covering a broad class of nonparametric estimators under mild complexity and noise conditions. When instantiated with deep ReLU networks, explicit convergence rates are derived under hierarchical composition models, demonstrating the ability to overcome the curse of dimensionality. Conditions that enable positive transfer with faster rates are considered, including learning with simpler functions and data augmentation through pooling samples across groups. Various simulations and real-data experiments further validate the effectiveness of the proposed method.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2608.20255 — 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 2026-10-18T11:47:43.392Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).