Metraipolis › archive › dc_577b87899736
Compact and Infinite-Order Error Analysis for Null-Space SVD Estimation — arXiv:2608.30374
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.30374
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:39:58.296Z
- SHA-256 of the archived text
f5c0533576ab78a306582f404fe3dfb9c07bbc05e3bc221635e3b5f1fed00484- Stable URL of this page
https://metraipolis.com/documento/dc_577b87899736
How to cite
Compact and Infinite-Order Error Analysis for Null-Space SVD Estimation — arXiv:2608.30374 — arXiv (en), https://arxiv.org/abs/2608.30374 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_577b87899736 (Metraipolis archive dc_577b87899736, sha256 f5c0533576ab78a306582f404fe3dfb9c07bbc05e3bc221635e3b5f1fed00484)
BibTeX
@misc{dc577b87899736,
title = {Compact and Infinite-Order Error Analysis for Null-Space SVD Estimation — arXiv:2608.30374},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.30374},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_577b87899736; sha256 f5c0533576ab78a306582f404fe3dfb9c07bbc05e3bc221635e3b5f1fed00484},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30374. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study null-space estimation from a noisy matrix. For a simple left null space, we first derive an exact compact expression for the error of the smallest left singular vector. We then give an all-order series for the SVD vector and projector, followed by compact and consistently truncated series forms for the fixed-realization empirical risk and conditional population generalization risk. The recursion extends to a multiple-dimensional null space by following the complete invariant subspace. The convergence radius is not inferred from an error plot: it is computed independently from the nearest complex exceptional point that joins a retained eigenvalue branch to its complement. A reduced-nullity experiment shows that moving this spectral boundary can increase the radius, although the improvement is not monotone in the retained nullity. For individually ordered null directions under Gaussian training with \(\tau\geq m\), we prove that the Wishart splitting matrix \(W\) gives a strict second-order empirical ranking. Gaussian averaging equalizes the leading generalization risks at both small and very large noise, while a column-swap theorem proves strict expected generalization ranking for an isotropic signal subspace. For unequal spikes, an exact population-overlap criterion and a simultaneous \(99\%\) Monte Carlo confidence certificate explain the observed intermediate ranking. A sixth-order risk correction improves the lower-crossover estimate in the reported experiment. This equal--ranked--equal phenomenon is a finite-sample diagnostic related to spectral mixing, but its tolerance crossings, the exceptional-point radius, and the asymptotic BBP threshold are three distinct quantities. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.LG). Categorie arXiv: Statistics Theory (math.ST) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.30374 — 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 2026-10-17T08:13:26.937Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).