Metraipolis › archive › dc_a3eb6dbd350a
Robust Multi-Task Learning for Principal Component Analysis — arXiv:2609.20733
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20733
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T04:15:56.089Z
- SHA-256 of the archived text
bad364be28374a78fcade9b3574d1fd25d7e2fd2b348511c7387c963485839f2- Stable URL of this page
https://metraipolis.com/documento/dc_a3eb6dbd350a
How to cite
Robust Multi-Task Learning for Principal Component Analysis — arXiv:2609.20733 — arXiv (en), https://arxiv.org/abs/2609.20733 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a3eb6dbd350a (Metraipolis archive dc_a3eb6dbd350a, sha256 bad364be28374a78fcade9b3574d1fd25d7e2fd2b348511c7387c963485839f2)
BibTeX
@misc{dca3eb6dbd350a,
title = {Robust Multi-Task Learning for Principal Component Analysis — arXiv:2609.20733},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20733},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a3eb6dbd350a; sha256 bad364be28374a78fcade9b3574d1fd25d7e2fd2b348511c7387c963485839f2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20733. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Principal component analysis (PCA) is a fundamental tool for learning low-dimensional structure from high-dimensional data. When data are collected from multiple sources, the underlying task distributions may exhibit unknown degrees of similarity, with some tasks potentially arising from arbitrary distributions. We propose new multi-task PCA procedures that exploit similarity structure across tasks to improve eigenspace estimation while remaining robust to outlier tasks. We establish non-asymptotic convergence rates and show that the proposed procedures attain minimax optimal rates in a range of regimes. One of the procedures builds on the matrix-depth notion of Chen, Gao, and Ren (2018) and can achieve the optimal dependence of the estimation error on the proportion of outlier tasks, addressing a key challenge in robust multi-task learning. Extensive simulations and real-data analyses demonstrate the effectiveness of the proposed methods. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in stat.ML). Categorie arXiv: Statistics Theory (math.ST) ; Methodology (stat.ME); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.20733 — 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 2026-10-10T04:02:52.988Z dalla pagina https://arxiv.org/catchup/stat.ML/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).