Metraipolis › archive › dc_47472fb28e02

Optimal rates for aggregation of affine estimators — arXiv:2609.07166

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07166
License (as archived)
CC0-1.0
Archived
2026-10-16T14:30:07.931Z
SHA-256 of the archived text
f63d0786afd27df0fb09a7e8e4d370ba63d12aae8f6049a1447b60488fce3824
Stable URL of this page
https://metraipolis.com/documento/dc_47472fb28e02

How to cite

Optimal rates for aggregation of affine estimators — arXiv:2609.07166 — arXiv (en), https://arxiv.org/abs/2609.07166 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_47472fb28e02 (Metraipolis archive dc_47472fb28e02, sha256 f63d0786afd27df0fb09a7e8e4d370ba63d12aae8f6049a1447b60488fce3824)
BibTeX
@misc{dc47472fb28e02,
  title = {Optimal rates for aggregation of affine estimators — arXiv:2609.07166},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07166},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_47472fb28e02; sha256 f63d0786afd27df0fb09a7e8e4d370ba63d12aae8f6049a1447b60488fce3824},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07166. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Aggregation of estimation procedures has found important applications in econometrics, statistics, and machine learning. Classical statistical aggregation theory has mainly focused on a \emph{pure aggregation} setting, where the candidate estimators are either deterministic or constructed using a held-out sample independent of that used for aggregation. When the candidate estimators and the aggregation weights are estimated from the same dataset without sample splitting, Bellec [\emph{Ann. Statist.} \textbf{46} (2018), 30--59] established the optimal rate for model-selection aggregation of affine estimators. Beyond this regime, however, fundamental questions regarding the optimal aggregation rates and the construction of aggregation rules attaining these rates remain largely unresolved. In this paper, we consider the problem of aggregating a finite collection of affine estimators to learn an optimal convex combination of them. This framework encompasses a rich class of estimators widely used in statistics and machine learning, including least squares estimators, kernel ridge estimators, random feature regression estimators, and among many others. We establish the minimax rate for convex aggregation of affine estimators. In particular, we show that estimating the weights by minimizing a Mallows' $C_p$ criterion attains the optimal rate. We further study the linear aggregation regime with unrestricted weights and establish matching minimax lower and upper bounds over suitable classes of affine estimators.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-09 in math.ST).
Categorie arXiv: Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2609.07166 — 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 2026-10-16T14:09:40.563Z dalla pagina https://arxiv.org/catchup/math.ST/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).