Inexact restoration with subsampled trust-region methods for finite-sum minimization

DOI10.1007/s10589-020-00196-wzbMath1445.90102arXiv1902.01710OpenAlexW3034723207WikidataQ113107254 ScholiaQ113107254MaRDI QIDQ2191786

Stefania Bellavia, Benedetta Morini, Nataša Krejić

Publication date: 26 June 2020

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

Full work available at URL: https://arxiv.org/abs/1902.01710

zbMATH Keywords

subsamplingtrust-region methodsinexact restorationlocal and global convergenceworst-case evaluation complexity

Mathematics Subject Classification ID

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

Related Items (6)

Inexact restoration for derivative-free expensive function minimization and applications ⋮ Inexact restoration for minimization with inexact evaluation both of the objective function and the constraints ⋮ Preface of the special issue dedicated to the XII Brazilian workshop on continuous optimization ⋮ Linesearch Newton-CG methods for convex optimization with noise ⋮ A stochastic first-order trust-region method with inexact restoration for finite-sum minimization ⋮ An inexact restoration-nonsmooth algorithm with variable accuracy for stochastic nonsmooth convex optimization problems in machine learning and stochastic linear complementarity problems

Uses Software

• UCI-ml
• LIBSVM
• MNIST

Cites Work

• Unnamed Item
• A Stochastic Quasi-Newton Method for Large-Scale Optimization
• On the convergence and worst-case complexity of trust-region and regularization methods for unconstrained optimization
• Sample size selection in optimization methods for machine learning
• An adaptive Monte Carlo algorithm for computing mixed logit estimators
• Efficient sample sizes in stochastic nonlinear programming
• Variable-number sample-path optimization
• Sub-sampled Newton methods
• Line search methods with variable sample size for unconstrained optimization
• Inexact-restoration algorithm for constrained optimization
• Newton-type methods for non-convex optimization under inexact Hessian information
• Nonmonotone line search methods with variable sample size
• Convergence theory for nonconvex stochastic programming with an application to mixed logit
• Inexact Restoration approach for minimization with inexact evaluation of the objective function
• Hybrid Deterministic-Stochastic Methods for Data Fitting
• Newton Sketch: A Near Linear-Time Optimization Algorithm with Linear-Quadratic Convergence
• On Choosing Parameters in Retrospective-Approximation Algorithms for Stochastic Root Finding and Simulation Optimization
• Numerical Optimization
• Trust Region Methods
• 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
• An investigation of Newton-Sketch and subsampled Newton methods
• Iteration and evaluation complexity for the minimization of functions whose computation is intrinsically inexact
• Adaptive Regularization Algorithms with Inexact Evaluations for Nonconvex Optimization
• Exact and inexact subsampled Newton methods for optimization
• Subsampled inexact Newton methods for minimizing large sums of convex functions
• Inexact-restoration method with Lagrangian tangent decrease and new merit function for nonlinear programming.

This page was built for publication: Inexact restoration with subsampled trust-region methods for finite-sum minimization