paper-with-me

홈 › Papers

Decentralized Non-convex Stochastic Optimization with Heterogeneous Variance

2026-02-12 · Hongxu Chen, Ke Wei, Luo Luo arxiv

Decentralized optimization is critical for solving large-scale machine learning problems over distributed networks, where multiple nodes collaborate through local communication. In practice, the variances of stochastic gradient estimators often differ across nodes, yet their impact on algorithm design and complexity remains unclear. To address this issue, we propose D-NSS, a decentralized algorithm with node-specific sampling, and establish its sample complexity depending on the arithmetic mean of local standard deviations, achieving tighter bounds than existing methods that rely on the worst-case or quadratic mean. We further derive a matching sample complexity lower bound under heterogeneous variance, thereby proving the optimality of this dependence. Moreover, we extend the framework with a variance reduction technique and develop D-NSS-VR, which under the mean-squared smoothness assumption attains an improved sample complexity bound while preserving the arithmetic-mean dependence. Finally, numerical experiments validate the theoretical results and demonstrate the effectiveness of the proposed algorithms.

📄 PDF Abstract BibTeX arXiv:2602.11789

Code (0)

등록된 구현이 없습니다.

Tasks

Stochastic Optimization

Similar Papers 제목 키워드 기반

Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise

2025-09-19 · Xinwen Zhang, Yihan Zhang, Heng Liang, Hongchang Gao arxiv

Existing decentralized stochastic optimization methods assume the lower-level loss function is strongly convex and the stochastic gradient noise has finite variance. These strong assumptions typically are not satisfied i…

Stochastic OptimizationBilevel Optimization

Decentralized Stochastic Variance Reduced Extragradient Method

2022-02-01 · Luo Luo, Haishan Ye

This paper studies decentralized convex-concave minimax optimization problems of the form $\min_x\max_y f(x,y) \triangleq\frac{1}{m}\sum_{i=1}^m f_i(x,y)$, where $m$ is the number of agents and each local function can be…

Accelerated Decentralized Stochastic Gradient Descent for Strongly Convex Optimization

2026-06-05 · Ming Sun, Kun Yuan arxiv

Decentralized stochastic optimization is a fundamental paradigm for large-scale learning over networks, where agents communicate only with their neighbors and no central coordinator is required. For strongly convex probl…

Stochastic Optimization

Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization

2024-06-03 · Emre Sahinoglu, Shahin Shahrampour

We investigate the finite-time analysis of finding ($\delta,\epsilon$)-stationary points for nonsmooth nonconvex objectives in decentralized stochastic optimization. A set of agents aim at minimizing a global function us…

Stochastic Optimization

Can Decentralized Stochastic Minimax Optimization Algorithms Converge Linearly for Finite-Sum Nonconvex-Nonconcave Problems?

2023-04-24 · Yihan Zhang, Wenhao Jiang, Feng Zheng, Chiu C. Tan 외

Decentralized minimax optimization has been actively studied in the past few years due to its application in a wide range of machine learning models. However, the current theoretical understanding of its convergence rate…