Metraipolis › archive › dc_632bdd98cbbc
On k-nearest-neighbor regression in metric spaces — arXiv:2610.41896
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41896
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T05:41:00.782Z
- SHA-256 of the archived text
01fc57871c20a7a88fd59d089c4c459b6f2a1cd316a34a029cf802e285d2ac4f- Stable URL of this page
https://metraipolis.com/documento/dc_632bdd98cbbc
How to cite
On k-nearest-neighbor regression in metric spaces — arXiv:2610.41896 — arXiv (en), https://arxiv.org/abs/2610.41896 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_632bdd98cbbc (Metraipolis archive dc_632bdd98cbbc, sha256 01fc57871c20a7a88fd59d089c4c459b6f2a1cd316a34a029cf802e285d2ac4f)
BibTeX
@misc{dc632bdd98cbbc,
title = {On k-nearest-neighbor regression in metric spaces — arXiv:2610.41896},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41896},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_632bdd98cbbc; sha256 01fc57871c20a7a88fd59d089c4c459b6f2a1cd316a34a029cf802e285d2ac4f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41896. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study mean squared consistency of k-nearest-neighbor regression for metric space valued features. For a fixed feature distribution mu with atomless distance distributions, we describe how neighbor selection redistributes probability through the density of a uniformly chosen neighbor of an independent query. This gives separate conditions for the approximation error and the conditional response variance, and weakens Stone's domination condition when stronger response moments are available. In particular, when k_n tends to infinity and k_n/n tends to zero, a uniform L2(mu) bound on the selection densities suffices under a finite fourth response moment. We give a corresponding condition in terms of neighborhoods of fixed population mass and recover the Euclidean density bound. Finite global Nagata dimension gives Stone's domination. While sigma-finite Nagata dimensionality is known to ensure universal consistency of k-NN classification in complete separable spaces, we show that this is not the case for mean squared consistency with unbounded responses: we construct a space in this class on which one fixed noiseless response with all finite moments has diverging mean squared error. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.41896 — 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 2026-11-03T05:26:25.722Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).