Metraipolis › archive › dc_4e356361dac7
P-GADMM: Parallel Group-Based ADMM for Asynchronous Optimization in Heterogeneous Edge Networks — arXiv:2609.20006
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20006
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T03:48:58.417Z
- SHA-256 of the archived text
11f7301987f7b18977b5a773f79067256aec75f560d41aaef069afb979bfbf6f- Stable URL of this page
https://metraipolis.com/documento/dc_4e356361dac7
How to cite
P-GADMM: Parallel Group-Based ADMM for Asynchronous Optimization in Heterogeneous Edge Networks — arXiv:2609.20006 — arXiv (en), https://arxiv.org/abs/2609.20006 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e356361dac7 (Metraipolis archive dc_4e356361dac7, sha256 11f7301987f7b18977b5a773f79067256aec75f560d41aaef069afb979bfbf6f)
BibTeX
@misc{dc4e356361dac7,
title = {P-GADMM: Parallel Group-Based ADMM for Asynchronous Optimization in Heterogeneous Edge Networks — arXiv:2609.20006},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20006},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e356361dac7; sha256 11f7301987f7b18977b5a773f79067256aec75f560d41aaef069afb979bfbf6f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20006. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The Alternating Direction Method of Multipliers (ADMM) is widely used for distributed optimization, but its synchronous implementation can suffer from efficiency loss in heterogeneous edge networks, where fast clients or groups need to wait for slower ones before global updates can be completed. Existing group-based ADMM methods reduce communication overhead through grouping, but their grouping rules usually focus on data similarity or network topology and do not explicitly account for computation heterogeneity. To address this issue, this paper proposes Parallel Group-Based ADMM (P-GADMM) for distributed optimization in heterogeneous edge networks. P-GADMM forms computation-aware edge groups according to client computational capabilities and local data sizes, which reduces training-speed variation within each group. It further combines edge-level aggregation with bounded asynchronous coordination at the cloud, allowing active groups to participate in global updates without waiting for slower groups while controlling stale group information through a delay threshold. For strongly convex group objectives, we establish convergence guarantees for an idealized form of P-GADMM under bounded group-level staleness, showing a time-averaged convergence behavior up to a staleness-induced asymptotic error neighborhood. Experiments show that P-GADMM reduces wall-clock training time compared with representative baselines while maintaining comparable final accuracy. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-18 in cs.DC). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC). Pagina del lavoro: https://arxiv.org/abs/2609.20006 — 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 2026-10-10T03:24:19.921Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).