Decentralized Nonsmooth Nonconvex Optimization with Client Sampling
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912852147699712 |
|---|---|
| author | Chen, Xinyan Gao, Weiguo Luo, Luo |
| author_facet | Chen, Xinyan Gao, Weiguo Luo, Luo |
| contents | This paper considers decentralized nonsmooth nonconvex optimization problem with Lipschitz continuous local functions. We propose an efficient stochastic first-order method with client sampling, achieving the $(δ,ε)$-Goldstein stationary point with the overall sample complexity of ${\mathcal O}(δ^{-1}ε^{-3})$, the computation rounds of ${\mathcal O}(δ^{-1}ε^{-3})$, and the communication rounds of ${\tilde{\mathcal O}}(γ^{-1/2}δ^{-1}ε^{-3})$, where $γ$ is the spectral gap of the mixing matrix for the network. Our results achieve the optimal sample complexity and the sharper communication complexity than existing methods. We also extend our ideas to zeroth-order optimization. Moreover, the numerical experiments show the empirical advantage of our methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_19381 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Decentralized Nonsmooth Nonconvex Optimization with Client Sampling Chen, Xinyan Gao, Weiguo Luo, Luo Optimization and Control Distributed, Parallel, and Cluster Computing This paper considers decentralized nonsmooth nonconvex optimization problem with Lipschitz continuous local functions. We propose an efficient stochastic first-order method with client sampling, achieving the $(δ,ε)$-Goldstein stationary point with the overall sample complexity of ${\mathcal O}(δ^{-1}ε^{-3})$, the computation rounds of ${\mathcal O}(δ^{-1}ε^{-3})$, and the communication rounds of ${\tilde{\mathcal O}}(γ^{-1/2}δ^{-1}ε^{-3})$, where $γ$ is the spectral gap of the mixing matrix for the network. Our results achieve the optimal sample complexity and the sharper communication complexity than existing methods. We also extend our ideas to zeroth-order optimization. Moreover, the numerical experiments show the empirical advantage of our methods. |
| title | Decentralized Nonsmooth Nonconvex Optimization with Client Sampling |
| topic | Optimization and Control Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2601.19381 |