Decentralized Gradient-Free Methods for Stochastic Non-Smooth Non-Convex Optimization

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lin, Zhenwei, Xia, Jingfan, Deng, Qi, Luo, Luo
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909467545698304
author Lin, Zhenwei
Xia, Jingfan
Deng, Qi
Luo, Luo
author_facet Lin, Zhenwei
Xia, Jingfan
Deng, Qi
Luo, Luo
contents We consider decentralized gradient-free optimization of minimizing Lipschitz continuous functions that satisfy neither smoothness nor convexity assumption. We propose two novel gradient-free algorithms, the Decentralized Gradient-Free Method (DGFM) and its variant, the Decentralized Gradient-Free Method$^+$ (DGFM$^{+}$). Based on the techniques of randomized smoothing and gradient tracking, DGFM requires the computation of the zeroth-order oracle of a single sample in each iteration, making it less demanding in terms of computational resources for individual computing nodes. Theoretically, DGFM achieves a complexity of $\mathcal O(d^{3/2}δ^{-1}\varepsilon ^{-4})$ for obtaining an $(δ,\varepsilon)$-Goldstein stationary point. DGFM$^{+}$, an advanced version of DGFM, incorporates variance reduction to further improve the convergence behavior. It samples a mini-batch at each iteration and periodically draws a larger batch of data, which improves the complexity to $\mathcal O(d^{3/2}δ^{-1} \varepsilon^{-3})$. Moreover, experimental results underscore the empirical advantages of our proposed algorithms when applied to real-world datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2310_11973
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Decentralized Gradient-Free Methods for Stochastic Non-Smooth Non-Convex Optimization
Lin, Zhenwei
Xia, Jingfan
Deng, Qi
Luo, Luo
Optimization and Control
Distributed, Parallel, and Cluster Computing
We consider decentralized gradient-free optimization of minimizing Lipschitz continuous functions that satisfy neither smoothness nor convexity assumption. We propose two novel gradient-free algorithms, the Decentralized Gradient-Free Method (DGFM) and its variant, the Decentralized Gradient-Free Method$^+$ (DGFM$^{+}$). Based on the techniques of randomized smoothing and gradient tracking, DGFM requires the computation of the zeroth-order oracle of a single sample in each iteration, making it less demanding in terms of computational resources for individual computing nodes. Theoretically, DGFM achieves a complexity of $\mathcal O(d^{3/2}δ^{-1}\varepsilon ^{-4})$ for obtaining an $(δ,\varepsilon)$-Goldstein stationary point. DGFM$^{+}$, an advanced version of DGFM, incorporates variance reduction to further improve the convergence behavior. It samples a mini-batch at each iteration and periodically draws a larger batch of data, which improves the complexity to $\mathcal O(d^{3/2}δ^{-1} \varepsilon^{-3})$. Moreover, experimental results underscore the empirical advantages of our proposed algorithms when applied to real-world datasets.
title Decentralized Gradient-Free Methods for Stochastic Non-Smooth Non-Convex Optimization
topic Optimization and Control
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2310.11973