Metraipolis › archive › dc_13ec2f16d2d8
The Geometry of Multitask Learning: Sharp Rates for Shared Subspace Estimation — arXiv:2610.40713
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40713
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T05:41:18.978Z
- SHA-256 of the archived text
21d1b8ed6cf5d0bf2695b6f6b88f3a4d82988c1d899555438780129cfcc7123c- Stable URL of this page
https://metraipolis.com/documento/dc_13ec2f16d2d8
How to cite
The Geometry of Multitask Learning: Sharp Rates for Shared Subspace Estimation — arXiv:2610.40713 — arXiv (en), https://arxiv.org/abs/2610.40713 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_13ec2f16d2d8 (Metraipolis archive dc_13ec2f16d2d8, sha256 21d1b8ed6cf5d0bf2695b6f6b88f3a4d82988c1d899555438780129cfcc7123c)
BibTeX
@misc{dc13ec2f16d2d8,
title = {The Geometry of Multitask Learning: Sharp Rates for Shared Subspace Estimation — arXiv:2610.40713},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40713},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_13ec2f16d2d8; sha256 21d1b8ed6cf5d0bf2695b6f6b88f3a4d82988c1d899555438780129cfcc7123c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40713. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Learning a shared subspace in multitask learning is an important statistical problem, yet exact rates remain poorly understood in many of the formal settings considered in the literature. To address this gap, which arises from limitations of existing upper-bound techniques, we propose a general multitask lemma. The lemma provides sufficient conditions for fast subspace estimation in generic multitask settings, in the form of geometric conditions on the task regression functions and their estimators. We subsequently show that the multitask lemma yields sharp minimax rates---previously unknown---for linear regression and classification in the regimes considered, and rates matching up to logarithmic factors for additive-noise regression. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Statistics Theory (math.ST). Pagina del lavoro: https://arxiv.org/abs/2610.40713 — 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 2026-11-03T05:26:25.906Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).