A non-monotone trust-region method with noisy oracles and additional sampling

DOI10.1007/S10589-024-00580-WMaRDI QIDQ6606856

Nataša Krklec Jerinkić, Nataša Krejić, Mahsa Yousefi, Angeles Martínez

Publication date: 17 September 2024

Published in: Computational Optimization and Applications (Search for Journal in Brave)

zbMATH Keywords

stochastic optimizationquasi-Newtonadaptive samplingsecond-order methodsdeep neural networks trainingnon-monotone trust-region

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Large-scale problems in mathematical programming (90C06) Applications of mathematical programming (90C90) Nonlinear programming (90C30) Stochastic programming (90C15) Methods of quasi-Newton type (90C53)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• On solving L-SR1 trust-region subproblems
• Minimizing finite sums with the stochastic average gradient
• Combining nonmonotone conic trust region and line search techniques for unconstrained optimization
• Nonmonotonic trust region algorithm
• Stochastic optimization using a trust-region method and random models
• A stochastic first-order trust-region method with inexact restoration for finite-sum minimization
• Nonmonotone line search methods with variable sample size
• A nonmonotone trust-region line search method for large-scale unconstrained optimization
• Global convergence of online limited memory BFGS
• Descent direction method with line search for unconstrained optimization in noisy environment
• Trust Region Methods
• Variance-Based Extragradient Methods with Line Search for Stochastic Variational Inequalities
• Optimization Methods for Large-Scale Machine Learning
• A Nonmonotone Line Search Technique for Newton’s Method
• A robust multi-batch L-BFGS method for machine learning
• Quasi-Newton methods for machine learning: forget the past, just sample
• Trust-region algorithms for training responses: machine learning methods using indefinite Hessian approximations
• Stochastic Quasi-Newton Methods for Nonconvex Stochastic Optimization
• A Stochastic Approximation Method
• Exact and inexact subsampled Newton methods for optimization
• LSOS: Line-search second-order stochastic optimization methods for nonconvex finite sums
• A trust region method for noisy unconstrained optimization
• First- and second-order high probability complexity bounds for trust-region methods with noisy oracles

This page was built for publication: A non-monotone trust-region method with noisy oracles and additional sampling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6606856)