A variance-reduced stochastic gradient tracking algorithm for decentralized optimization with orthogonality constraints

DOI10.3934/jimo.2023018zbMath1524.90221arXiv2208.13643OpenAlexW4321795558MaRDI QIDQ6175371

Lei Wang, Xin Liu

Publication date: 21 July 2023

Published in: Journal of Industrial and Management Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2208.13643

zbMATH Keywords

Stiefel manifoldvariance reductiondecentralized optimizationorthogonality constraintsstochastic gradient tracking

Mathematics Subject Classification ID

Large-scale problems in mathematical programming (90C06) Nonlinear programming (90C30) Stochastic programming (90C15)

Cites Work

• Unnamed Item
• A brief introduction to manifold optimization
• Quadratic optimization with orthogonality constraint: explicit Łojasiewicz exponent and linear convergence of retraction-based line-search and stochastic variance-reduced gradient methods
• Perturbed proximal primal-dual algorithm for nonconvex nonsmooth optimization
• Fast linear iterations for distributed averaging
• On the Convergence of Decentralized Gradient Descent
• Decentralized Eigenvalue Algorithms for Distributed Signal Detection in Wireless Networks
• Multi-Agent Distributed Optimization via Inexact Consensus ADMM
• DLM: Decentralized Linearized Alternating Direction Method of Multipliers
• Cloud K-SVD: A Collaborative Dictionary Learning Algorithm for Big, Distributed Data
• On Nonconvex Decentralized Gradient Descent
• Harnessing Smoothness to Accelerate Distributed Optimization
• Distributed Subgradient Methods for Multi-Agent Optimization
• Fast Decentralized Nonconvex Finite-Sum Optimization with Recursive Variance Reduction
• A class of smooth exact penalty function methods for optimization problems with orthogonality constraints
• Parallelizable Algorithms for Optimization Problems with Orthogonality Constraints
• Riemannian Stochastic Variance Reduced Gradient Algorithm with Retraction and Vector Transport
• EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization
• A decentralized algorithm for spectral analysis

This page was built for publication: A variance-reduced stochastic gradient tracking algorithm for decentralized optimization with orthogonality constraints