Distributed Riemannian stochastic gradient tracking algorithm on the Stiefel manifold

DOI10.1016/J.AUTOMATICA.2025.112726MaRDI QIDQ6879150zbMATH OpenFDO

Authors Jishu Zhao, Xi Wang, Jinlong Lei

Publication date 2 January 2026

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.AUTOMATICA.2025.112726

zbMATH Keywords

distributed stochastic optimizationgradient trackingRiemannian optimizationvariable sampling scheme

Mathematics Subject Classification ID

Optimal stochastic control (93E20)

Cites work

• A decentralized algorithm for spectral analysis
• A decentralized proximal gradient tracking algorithm for composite optimization on Riemannian manifolds
• A Stochastic Approximation Method
• A variance-reduced stochastic gradient tracking algorithm for decentralized optimization with orthogonality constraints
• Adaptation, learning, and optimization over networks
• Cloud K-SVD: A Collaborative Dictionary Learning Algorithm for Big, Distributed Data
• Consensus optimization on manifolds
• Convergence speed in distributed consensus and averaging
• Decentralized optimization over the Stiefel manifold by an approximate augmented Lagrangian function
• Decentralized projected Riemannian gradient method for smooth optimization on compact submanifolds embedded in the Euclidean space
• Distributed Coupled Multiagent Stochastic Optimization
• Distributed stochastic gradient tracking methods
• Distributed Variable Sample-Size Stochastic Optimization With Fixed Step-Sizes
• Global rates of convergence for nonconvex optimization on manifolds
• Harnessing Smoothness to Accelerate Distributed Optimization
• High-dimensional Kuramoto models on Stiefel manifolds synchronize complex networks almost globally
• scientific article; zbMATH DE number 5223994 (Why is no real title available?)
• On the local linear rate of consensus on the Stiefel manifold
• Optimization methods for large-scale machine learning
• Perturbation Bounds of Unitary and Subunitary Polar Factors
• Pymanopt: a Python toolbox for optimization on manifolds using automatic differentiation
• Quadratic optimization with orthogonality constraint: explicit Łojasiewicz exponent and linear convergence of retraction-based line-search and stochastic variance-reduced gradient methods
• Riemannian center of mass and mollifier smoothing
• Stochastic Gradient Descent on Riemannian Manifolds
• The Geometry of Algorithms with Orthogonality Constraints
• Weakly convex optimization over Stiefel manifold using Riemannian subgradient-type methods

This page was built for publication: Distributed Riemannian stochastic gradient tracking algorithm on the Stiefel manifold

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6879150)