Metraipolis › archive › dc_e4eb5cbc76e6

Dimension-Free Decentralized Nonsmooth Nonconvex Stochastic Optimization — arXiv:2610.05789

Source
arXiv
Original
https://arxiv.org/abs/2610.05789
License (as archived)
CC0-1.0
Archived
2026-10-06T05:32:22.003Z
SHA-256 of the archived text
57bd11a2fe16cc1d22c96d430e0d5a8597e3916938336294b170519903e6e925
Stable URL of this page
https://metraipolis.com/documento/dc_e4eb5cbc76e6

How to cite

Dimension-Free Decentralized Nonsmooth Nonconvex Stochastic Optimization — arXiv:2610.05789 — arXiv, https://arxiv.org/abs/2610.05789 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e4eb5cbc76e6 (Metraipolis archive dc_e4eb5cbc76e6, sha256 57bd11a2fe16cc1d22c96d430e0d5a8597e3916938336294b170519903e6e925)
BibTeX
@misc{dce4eb5cbc76e6,
  title = {Dimension-Free Decentralized Nonsmooth Nonconvex Stochastic Optimization — arXiv:2610.05789},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05789},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e4eb5cbc76e6; sha256 57bd11a2fe16cc1d22c96d430e0d5a8597e3916938336294b170519903e6e925},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05789. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We investigate decentralized nonsmooth nonconvex stochastic optimization over a network of $n$ nodes, with the goal of finding an $(\delta,\epsilon)$-Goldstein stationary point. The best existing algorithm achieves $O(\delta^{-1}(\epsilon^{-3}+d\epsilon^{-1}))$ sample complexity and $\widetilde{O}(\gamma^{-1/2}\delta^{-1}(\epsilon^{-3}+d\epsilon^{-1}))$ communication complexity, where $d$ is the problem dimension and $\gamma$ is the spectral gap of the communication matrix. However, the polynomial dependence on $d$ can be a major bottleneck in high-dimensional regimes. In this paper, we propose a novel algorithm that achieves $O(\delta^{-1}\epsilon^{-3})$ sample complexity and $\widetilde{O}(\gamma^{-1/2}\delta^{-1}\epsilon^{-3})$ communication complexity. The primary technique is an elegant decentralized online-to-nonconvex conversion that reduces the original problem to a decentralized online convex optimization (D-OCO) problem. A key property of our conversion is that its consensus requirements can be inherited directly from the consensus of the underlying D-OCO decisions. In particular, this property enables us to establish an explicit connection between the dimension dependence and the consensus error, which in turn shows that the polynomial dependence on $d$ can be removed with only logarithmic additional communication.

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/2610.05789 — 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 2026-10-06T05:27:06.012Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).