An accelerated stochastic trust region method for stochastic optimization

MaRDI QIDQ7232373zbMATH OpenFDO

Authors Rulei Qi, Dan Xue, Jing Li, Yujia Zhai

Publication date 23 April 2026

Published in Journal of Computational Mathematics (Search for Journal in Brave)

Full work available at URL https://global-sci.com/JCM/article/view/22797

zbMATH Keywords

gradient descent methodmachine learningstochastic optimizationstochastic variance reduced gradienttrust region

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Stochastic programming (90C15)

Cites work

• A fully stochastic second-order trust region method
• A linearly convergent stochastic recursive gradient method for convex optimization
• A Stochastic Approximation Method
• A stochastic trust-region framework for policy optimization
• Accelerated stochastic variance reduction for a class of convex optimization problems
• Accelerating variance-reduced stochastic gradient methods
• Don't jump through hoops and remove those loops: SVRG and Katyusha are better without the outer loop
• Katyusha: the first direct acceleration of stochastic gradient methods
• Optimization methods for large-scale machine learning
• Stochastic Gradient Descent on Riemannian Manifolds
• Stochastic trust-region methods with trust-region radius depending on probabilistic models
• Stochastic variance reduced gradient methods using a trust-region-like scheme

This page was built for publication: An accelerated stochastic trust region method for stochastic optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7232373)