Metraipolis › archive › dc_e8ace477b515
Optimal spectral shrinkage via Krylov approximation — arXiv:2611.02122
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02122
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:42:36.055Z
- SHA-256 of the archived text
e0ac6d990ba20b701163d7eb9b60a2cc9a7f7824fc0a32697efc000dc3111ff6- Stable URL of this page
https://metraipolis.com/documento/dc_e8ace477b515
How to cite
Optimal spectral shrinkage via Krylov approximation — arXiv:2611.02122 — arXiv (en), https://arxiv.org/abs/2611.02122 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e8ace477b515 (Metraipolis archive dc_e8ace477b515, sha256 e0ac6d990ba20b701163d7eb9b60a2cc9a7f7824fc0a32697efc000dc3111ff6)
BibTeX
@misc{dce8ace477b515,
title = {Optimal spectral shrinkage via Krylov approximation — arXiv:2611.02122},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02122},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e8ace477b515; sha256 e0ac6d990ba20b701163d7eb9b60a2cc9a7f7824fc0a32697efc000dc3111ff6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02122. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Spectral shrinkage encompasses a broad family of estimators for high-dimensional linear regression that regularize estimation and prediction by applying spectral filters to the sample covariance matrix. Despite its widespread use, achieving oracle-optimal prediction risk under general covariance structures remains challenging, as the oracle filter requires unknown population quantities and has a closed form only for specific covariance models such as isotropic and spiked models. We propose \textit{risk-targeted Krylov fitting} (RTK), a data-driven spectral estimator that adapts to the unknown covariance structure and attains the oracle risk asymptotically. Like partial least squares, RTK operates in an $m$-dimensional Krylov space, but it targets the oracle risk directly by minimizing the leave-one-out risk, which we compute exactly without refitting the model $n$ times. Under general distributions and covariance structures, RTK attains the optimal prediction risk in the Krylov space up to $O(1/n)$. Furthermore, its risk approaches that of the optimal analytic filter with $m$ of order $\log n$. In simulations over a wide range of covariance structures, RTK and a truncated variant were robust to the choice of $m$ and consistently among the spectral estimators closest to the oracle. In applications to single-cell sequencing data and large-scale neural recordings, the proposed methods achieved higher prediction accuracy than competing estimators on most tasks.
Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ML, nuovi lavori del giorno).
Categorie arXiv: Methodology (stat.ME) ; Statistics Theory (math.ST); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.02122 — 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 2026-11-03T18:13:37.696Z dalla pagina https://arxiv.org/list/stat.ML/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).