Metraipolis › archive › dc_45aec607a30e

Ensembles of Random Partition-Based Models under Covariate Shift — arXiv:2611.05195

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05195
License (as archived)
CC0-1.0
Archived
2026-11-04T18:54:25.738Z
SHA-256 of the archived text
c64c0a1eca20e73a6d5d0c1e67ecf42cfb3154613049db6fc172b1c62178adf9
Stable URL of this page
https://metraipolis.com/documento/dc_45aec607a30e

How to cite

Ensembles of Random Partition-Based Models under Covariate Shift — arXiv:2611.05195 — arXiv (en), https://arxiv.org/abs/2611.05195 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_45aec607a30e (Metraipolis archive dc_45aec607a30e, sha256 c64c0a1eca20e73a6d5d0c1e67ecf42cfb3154613049db6fc172b1c62178adf9)
BibTeX
@misc{dc45aec607a30e,
  title = {Ensembles of Random Partition-Based Models under Covariate Shift — arXiv:2611.05195},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05195},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_45aec607a30e; sha256 c64c0a1eca20e73a6d5d0c1e67ecf42cfb3154613049db6fc172b1c62178adf9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05195. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Distribution shifts, including covariate shifts, are ubiquitous in real-world applications of machine learning. Empirical evidence suggests that, across a variety of models with and without downstream adaptation, ensembles tend to be more robust to covariate shift than single models. We extend the theory of covariate shift severity from single models to ensembles, providing theoretical justification for the empirical trends. We introduce new discrepancy measures of covariate shift severity to control the risk of partition-based kernel estimators. We then show that with sufficient ensemble size, these models can achieve minimax-optimal risk convergence rates under covariate shift. Our results suggest that modelers can expect to need larger ensemble sizes for more severe covariate shifts.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2611.05195 — 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 2026-11-04T18:35:37.485Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).