Metraipolis › archive › dc_84ce0744ca71

Bias-Corrected Subspace Intersection: Minimax-Optimal Shared Subspace Estimation in Multi-View Data — arXiv:2609.05617

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05617
License (as archived)
CC0-1.0
Archived
2026-10-16T14:09:32.427Z
SHA-256 of the archived text
48e2f35ef032357694f27b3177f1a4fd4f242b207510eaf174016413fc5ae6f8
Stable URL of this page
https://metraipolis.com/documento/dc_84ce0744ca71

How to cite

Bias-Corrected Subspace Intersection: Minimax-Optimal Shared Subspace Estimation in Multi-View Data — arXiv:2609.05617 — arXiv (en), https://arxiv.org/abs/2609.05617 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_84ce0744ca71 (Metraipolis archive dc_84ce0744ca71, sha256 48e2f35ef032357694f27b3177f1a4fd4f242b207510eaf174016413fc5ae6f8)
BibTeX
@misc{dc84ce0744ca71,
  title = {Bias-Corrected Subspace Intersection: Minimax-Optimal Shared Subspace Estimation in Multi-View Data — arXiv:2609.05617},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05617},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_84ce0744ca71; sha256 48e2f35ef032357694f27b3177f1a4fd4f242b207510eaf174016413fc5ae6f8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05617. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Estimating a low-dimensional subspace shared across noisy data matrices is a fundamental problem in multi-view matrix estimation. We study this problem under the two-view JIVE model, where each data matrix contains shared and view-specific low-rank components. We demonstrate that standard plug-in subspace intersection, including AJIVE, suffers from a second-order bias caused by direction-dependent leakage of the empirical singular vectors. We propose bias-corrected subspace intersection (BCSI), which removes this bias before estimating the shared subspace. We establish finite-sample risk bounds for BCSI that accommodate unequal view dimensions, signal strengths, and view-specific ranks and require no condition-number assumptions on the signal matrices. When the shared and view-specific ranks are comparable, these bounds match our minimax lower bounds up to universal constants. The resulting minimax rate contains a new second-order term, arising from quadratic leakage perturbations relative to the shrinking spectral gap when the view-specific subspaces are nearly aligned. This term is absent from previous JIVE minimax lower bounds. Numerical experiments demonstrate the advantage of BCSI over AJIVE when the leakage bias is pronounced. Along the way, we establish a nonasymptotic concentration result for the bias-corrected leakage Gram matrix of a rectangular spiked matrix, which may be of independent interest.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in stat.ML).
Categorie arXiv: Methodology (stat.ME) ; Information Theory (cs.IT); Statistics Theory (math.ST); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.05617 — 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 2026-10-16T13:59:13.698Z dalla pagina https://arxiv.org/catchup/stat.ML/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).