Stochastic Gauss-Newton algorithm with STORM estimators for nonconvex composite optimization

DOI10.1007/s12190-022-01722-1zbMath1499.65237OpenAlexW4220922236WikidataQ114206554 ScholiaQ114206554MaRDI QIDQ2103169

Zhaoxin Wang, Bo Wen

Publication date: 13 December 2022

Published in: Journal of Applied Mathematics and Computing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s12190-022-01722-1

zbMATH Keywords

stochastic optimizationnonconvex optimizationmomentumoracle complexity

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Nonconvex programming, global optimization (90C26) Stochastic programming (90C15)

Related Items (1)

Hybrid SGD algorithms to solve stochastic composite optimization problems with application in sparse portfolio selection problems

Uses Software

• Adam

Cites Work

• Unnamed Item
• Unnamed Item
• Accelerated gradient methods for nonconvex nonlinear and stochastic programming
• Stochastic variance-reduced prox-linear algorithms for nonconvex composite optimization
• Complexity of stochastic dual dynamic programming
• Statistical estimation of composite risk functionals and risk optimization problems
• Modified Gauss–Newton scheme with worst case guarantees for global performance

This page was built for publication: Stochastic Gauss-Newton algorithm with STORM estimators for nonconvex composite optimization