A single timescale stochastic quasi-Newton method for stochastic optimization

DOI10.1080/00207160.2023.2269430MaRDI QIDQ6193377

De-Tong Zhu, Peng Wang

Publication date: 13 February 2024

Published in: International Journal of Computer Mathematics (Search for Journal in Brave)

zbMATH Keywords

stochastic optimizationmachine learningquasi-Newton methodBFGS update technique

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Nonlinear programming (90C30) Derivative-free methods and methods using generalized derivatives (90C56) Numerical methods based on nonlinear programming (49M37)

Cites Work

• Unnamed Item
• Unnamed Item
• A Stochastic Quasi-Newton Method for Large-Scale Optimization
• Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions
• Statistical estimation of composite risk functionals and risk optimization problems
• Convergence theory for nonconvex stochastic programming with an application to mixed logit
• Stochastic simulation: Algorithms and analysis
• Global Convergence of Online Limited Memory BFGS
• A Linearization Method for Nonsmooth Stochastic Programming Problems
• Adaptive Sampling Strategies for Stochastic Optimization
• RES: Regularized Stochastic BFGS Algorithm
• Multilevel Stochastic Gradient Methods for Nested Composition Optimization
• Accelerating Stochastic Composition Optimization
• A Single Timescale Stochastic Approximation Method for Nested Stochastic Optimization
• Understanding Machine Learning
• Stochastic Quasi-Newton Methods for Nonconvex Stochastic Optimization
• Benchmarking optimization software with performance profiles.

This page was built for publication: A single timescale stochastic quasi-Newton method for stochastic optimization