Metraipolis › archive › dc_7f4eb861445c
Incremental Aggregation on the Grassmannian for Asynchronous Eigenspace Computation — arXiv:2608.04406
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04406
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:36:52.252Z
- SHA-256 of the archived text
e62bbc6f27aeb0cf18ccd6f4b6bca8165791e26de21e24d14e4f9923bcade764- Stable URL of this page
https://metraipolis.com/documento/dc_7f4eb861445c
How to cite
Incremental Aggregation on the Grassmannian for Asynchronous Eigenspace Computation — arXiv:2608.04406 — arXiv (en), https://arxiv.org/abs/2608.04406 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7f4eb861445c (Metraipolis archive dc_7f4eb861445c, sha256 e62bbc6f27aeb0cf18ccd6f4b6bca8165791e26de21e24d14e4f9923bcade764)
BibTeX
@misc{dc7f4eb861445c,
title = {Incremental Aggregation on the Grassmannian for Asynchronous Eigenspace Computation — arXiv:2608.04406},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04406},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7f4eb861445c; sha256 e62bbc6f27aeb0cf18ccd6f4b6bca8165791e26de21e24d14e4f9923bcade764},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04406. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study asynchronous optimization for finite-sum eigenspace computation in heterogeneous distributed systems. The theoretical foundations for asynchronous eigenspace computation remain scarce, with existing approaches offering limited coverage of dynamics directly on the Grassmannian under stale information. In this paper, we propose a Grassmannian incremental aggregation method that refreshes only arriving components and reuses cached gradients, retaining low per-update cost without global synchronization. The method employs an extrinsic polar update that preserves the intrinsic subspace geometry without requiring parallel transport of stale tangent vectors. Our analysis establishes a tight angle-dependent gradient-dominance characterization of the objective and a basin-invariance property for stale aggregated updates. These yield two-phase linear convergence, comprising an explicit broad-basin regime and a sharper local regime, with constants controlled by component spectral spreads. Experiments on serial and distributed PCA demonstrate improved sample efficiency and wall-clock convergence over representative baselines. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-06 in stat.ML). Categorie arXiv: Optimization and Control (math.OC) ; Signal Processing (eess.SP); Numerical Analysis (math.NA); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2608.04406 — 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 2026-10-31T11:26:57.123Z dalla pagina https://arxiv.org/catchup/stat.ML/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).