Metraipolis › archive › dc_9afe4226271b
A Momentum-Based Variance-Reduced Algorithm for Federated Multiobjective Optimization — arXiv:2608.22945
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.22945
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T08:25:47.287Z
- SHA-256 of the archived text
ea5541c3232372b3787592e79d6e8af5160a6fbbcb0564806d1f33edcc93a3ae- Stable URL of this page
https://metraipolis.com/documento/dc_9afe4226271b
How to cite
A Momentum-Based Variance-Reduced Algorithm for Federated Multiobjective Optimization — arXiv:2608.22945 — arXiv (en), https://arxiv.org/abs/2608.22945 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9afe4226271b (Metraipolis archive dc_9afe4226271b, sha256 ea5541c3232372b3787592e79d6e8af5160a6fbbcb0564806d1f33edcc93a3ae)
BibTeX
@misc{dc9afe4226271b,
title = {A Momentum-Based Variance-Reduced Algorithm for Federated Multiobjective Optimization — arXiv:2608.22945},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.22945},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9afe4226271b; sha256 ea5541c3232372b3787592e79d6e8af5160a6fbbcb0564806d1f33edcc93a3ae},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22945. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Federated learning has traditionally been formulated as a single-objective optimization problem, primarily focused on maximizing model utility. In real-world applications, however, machine learning models often need to optimize multiple and potentially conflicting objectives simultaneously. This motivates federated multiobjective optimization (FMOO), which provides a natural framework for jointly handling multiple task-specific objectives in federated learning. In this paper, we propose a momentum-based variance-reduced algorithm for federated multiobjective optimization. The method incorporates a momentum-driven gradient estimator into the local updates to reduce the variance of stochastic updates, leading to an improved convergence rate. We establish theoretical guarantees showing that the expected Pareto stationarity measure of a randomly selected output iterate decays at a rate of $\mathcal{O}(T^{-2/3})$, improving upon the $\mathcal{O}(T^{-1/2})$ rates established for existing methods such as FSMGDA and FedCMOO. Numerical experiments on federated multiobjective optimization benchmarks demonstrate the effectiveness and competitive performance of the proposed algorithm.
Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-25 in math.OC).
Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2608.22945 — 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 2026-10-18T08:18:05.723Z dalla pagina https://arxiv.org/catchup/math.OC/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).