Metraipolis › archive › dc_89378c8f3f4a
CED-EF: Compressed Exact Diffusion with Error Feedback for Multi-Agent Learning — arXiv:2608.23013
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.23013
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:50:17.701Z
- SHA-256 of the archived text
f84112478ad777f450a335ae0a3ae7ab793392a6ec2a103372e48200d9af173a- Stable URL of this page
https://metraipolis.com/documento/dc_89378c8f3f4a
How to cite
CED-EF: Compressed Exact Diffusion with Error Feedback for Multi-Agent Learning — arXiv:2608.23013 — arXiv (en), https://arxiv.org/abs/2608.23013 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_89378c8f3f4a (Metraipolis archive dc_89378c8f3f4a, sha256 f84112478ad777f450a335ae0a3ae7ab793392a6ec2a103372e48200d9af173a)
BibTeX
@misc{dc89378c8f3f4a,
title = {CED-EF: Compressed Exact Diffusion with Error Feedback for Multi-Agent Learning — arXiv:2608.23013},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.23013},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_89378c8f3f4a; sha256 f84112478ad777f450a335ae0a3ae7ab793392a6ec2a103372e48200d9af173a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23013. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study decentralized stochastic optimization over a network of $N$ agents under compressed communication. We propose CED-EF, an exact diffusion-based method with error feedback that directly accommodates biased $\delta$-contractive compressors while communicating one compressed model-sized vector per node per iteration. For smooth nonconvex objectives with unbiased stochastic gradients whose variance is bounded by $\sigma^2$, where $\sigma\geq0$, we establish a convergence rate whose leading stochastic term is $\mathcal O(\sigma/\sqrt{NK})$. For $\sigma>0$, the dominant dependence of the corresponding transient time on the number of agents, compression level, and spectral gap $\Delta_\lambda$ is $\mathcal O(N^3/(\delta^4\Delta_\lambda^4))$, with fixed problem-dependent factors suppressed. Under the Polyak--Łojasiewicz condition, CED-EF attains a leading stochastic term $\widetilde{\mathcal O}(\sigma^2/(NK))$ with transient time on the order of $\widetilde{\mathcal O}(N/(\delta^2\Delta_\lambda^2))$. These dependencies improve the compression and/or network dependence of existing results. Numerical experiments on least-squares and logistic-regression problems illustrate the performance advantages of CED-EF.
Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-25 in cs.DC).
Categorie arXiv: Optimization and Control (math.OC) ; Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2608.23013 — 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 2026-10-18T07:47:32.969Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).