A stochastic first-order trust-region method with inexact restoration for finite-sum minimization

DOI10.1007/s10589-022-00430-7OpenAlexW3179487015MaRDI QIDQ2111466

Stefania Bellavia, Benedetta Morini, Nataša Krejić, Simone Rebegoldi

Publication date: 16 January 2023

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

Full work available at URL: https://arxiv.org/abs/2107.03129

zbMATH Keywords

subsamplingtrust-region methodsworst-case iteration complexityinexact restorationfinite-sum minimization

Mathematics Subject Classification ID

Abstract computational complexity for mathematical programming problems (90C60) Nonlinear programming (90C30)

Related Items (2)

Inexact restoration for minimization with inexact evaluation both of the objective function and the constraints ⋮ Special issue for SIMAI 2020-2021: large-scale optimization and applications

Uses Software

• UCI-ml
• LIBSVM
• Adam

Cites Work

• Unnamed Item
• Unnamed Item
• Minimizing finite sums with the stochastic average gradient
• Global convergence rate analysis of unconstrained optimization methods based on probabilistic models
• Stochastic optimization using a trust-region method and random models
• Inexact-restoration algorithm for constrained optimization
• Adaptive regularization for nonconvex optimization using inexact function values and randomly perturbed derivatives
• Inexact restoration with subsampled trust-region methods for finite-sum minimization
• Inexact Restoration approach for minimization with inexact evaluation of the objective function
• Convergence of Trust-Region Methods Based on Probabilistic Models
• On the employment of inexact restoration for the minimization of functions whose evaluation is subject to errors
• Optimization Methods for Large-Scale Machine Learning
• Adaptive cubic regularization methods with dynamic inexact Hessian information and applications to finite-sum minimization
• Global Convergence Rate Analysis of a Generic Line Search Algorithm with Noise
• Stochastic Trust-Region Methods with Trust-Region Radius Depending on Probabilistic Models
• A Stochastic Line Search Method with Expected Complexity Analysis
• Iteration and evaluation complexity for the minimization of functions whose computation is intrinsically inexact
• A Stochastic Approximation Method
• Trust-region algorithms: probabilistic complexity and intrinsic noise with applications to subsampling techniques

This page was built for publication: A stochastic first-order trust-region method with inexact restoration for finite-sum minimization