Metraipolis › archive › dc_acdbcd5e9080
From Mixing to Tearing: Graph Decomposition in Decentralized Optimization via Message Passing — arXiv:2610.03709
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.03709
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T23:10:57.964Z
- SHA-256 of the archived text
79b16fb9831abd770077febd6c3f4355e03782604ba17092cdd3e0b1e75219eb- Stable URL of this page
https://metraipolis.com/documento/dc_acdbcd5e9080
How to cite
From Mixing to Tearing: Graph Decomposition in Decentralized Optimization via Message Passing — arXiv:2610.03709 — arXiv, https://arxiv.org/abs/2610.03709 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_acdbcd5e9080 (Metraipolis archive dc_acdbcd5e9080, sha256 79b16fb9831abd770077febd6c3f4355e03782604ba17092cdd3e0b1e75219eb)
BibTeX
@misc{dcacdbcd5e9080,
title = {From Mixing to Tearing: Graph Decomposition in Decentralized Optimization via Message Passing — arXiv:2610.03709},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.03709},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_acdbcd5e9080; sha256 79b16fb9831abd770077febd6c3f4355e03782604ba17092cdd3e0b1e75219eb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03709. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study the minimization of sums of smooth strongly convex functions over undirected graphs, with each function held by one agent and communication restricted to neighbors in the graph. Existing decentralized methods, whether based on gossip or on routing over spanning trees, typically use the network to mix or aggregate information to enable {\it prescribed} local optimization updates. What this communication-centered viewpoint lacks is a general framework that uses graph structure to {\it jointly} design the optimization subproblems and the cooperative computation and communication through which agents solve them cooperatively. We develop such a framework from first principles, jointly designing the linear representation of agreement constraints, the blocks of the resulting dual variables (jointly optimized), and connected cluster of agents that cooperatively solve each block subproblem over the assigned subgraph. GATE (Graph-Tearing message passing) is a first instance of this framework: one variable per edge and tree blocks. At each iteration, agents update their assigned edge variables by minimizing the sum of the two endpoint cost-to-go messages and relaxing the result. The messages are updated through local minimizations following the tree recursion. To reduce per-iteration computational and communication costs, we develop GATE-S, a surrogate variant using tractable local models and lightweight message parametrizations. We establish linear convergence with a rate explicit in the interplay among function regularity, network topology, and the chosen partition, revealing the effects of graph decomposition. Numerical experiments are conducted to validate the theoretical results and evaluate the efficiency of our algorithms.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.03709 — 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 2026-10-05T23:01:38.788Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).