Metraipolis › archive › dc_8bacee29bba8

pESTO: Iterative p-greedy kernel regression with risk-driven Early STOpping — arXiv:2611.08555

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08555
License (as archived)
CC0-1.0
Archived
2026-11-09T22:41:48.363Z
SHA-256 of the archived text
5d9e9f94f9e109ff54ab15befb4d9fe632b04eed489ff6cbf5771dc8f62634d4
Stable URL of this page
https://metraipolis.com/documento/dc_8bacee29bba8

How to cite

pESTO: Iterative p-greedy kernel regression with risk-driven Early STOpping — arXiv:2611.08555 — arXiv (en), https://arxiv.org/abs/2611.08555 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8bacee29bba8 (Metraipolis archive dc_8bacee29bba8, sha256 5d9e9f94f9e109ff54ab15befb4d9fe632b04eed489ff6cbf5771dc8f62634d4)
BibTeX
@misc{dc8bacee29bba8,
  title = {pESTO: Iterative p-greedy kernel regression with risk-driven Early STOpping — arXiv:2611.08555},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08555},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8bacee29bba8; sha256 5d9e9f94f9e109ff54ab15befb4d9fe632b04eed489ff6cbf5771dc8f62634d4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08555. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Kernel-based greedy algorithms select suitable approximation nodes by minimizing point-wise error indicators, such as the power function; in this context, they are usually referred to as p-greedy approaches. In the presence of noisy data, deterministic criteria may fail, as the discrepancy between the true solution and its estimate is influenced by both approximation error and noise amplification, and the balance between the two is unknown. This study explicitly separates these two contributions, which are governed by the power function and a Lebesgue-type term, respectively. These bounds motivate the use of the Stein's unbiased risk estimator (SURE) as a proxy of the mean squared error, which in turn provides a principled and computable stopping criterion for the number of nodes to select in the p-greedy procedure. Numerical experiments demonstrate that this approach effectively balances deterministic accuracy and statistical noise contributions.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.08555 — 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 2026-11-09T22:33:47.169Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).