Stochastic trust-region and direct-search methods: a weak tail bound condition and reduced sample sizing

DOI10.1137/22M1543446MaRDI QIDQ6561380zbMATH OpenFDO

Authors F. Rinaldi, L. N. Vicente, Damiano Zeffiro

Publication date 25 June 2024

Published in SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/22M1543446

zbMATH Keywords

derivative-freedirect searchstochastic optimizationtrust region

Mathematics Subject Classification ID

Stochastic programming (90C15) Nonlinear programming (90C30) Derivative-free methods and methods using generalized derivatives (90C56)

Recommendations

• Stochastic derivative-free optimization using a trust region framework
• Expected complexity analysis of stochastic direct-search
• Convergence of trust-region methods based on probabilistic models
• Stochastic optimization using a trust-region method and random models
• Stochastic trust-region algorithm in random subspaces with convergence and expected complexity analyses

Cites work

• A Derivative-Free Algorithm for Linearly Constrained Finite Minimax Problems
• A Linesearch-Based Derivative-Free Approach for Nonsmooth Constrained Optimization
• A stochastic line search method with expected complexity analysis
• Adaptive regularization for nonconvex optimization using inexact function values and randomly perturbed derivatives
• An introduction to measure theory
• ASTRO-DF: a class of adaptive sampling trust-region algorithms for derivative-free stochastic optimization
• Benchmarking Derivative-Free Optimization Algorithms
• Computation of sparse low degree interpolating polynomials and their application to derivative-free optimization
• Constrained stochastic blackbox optimization using a progressive barrier and probabilistic estimates
• Convergence of trust-region methods based on probabilistic models
• Derivative-free and blackbox optimization
• Expected complexity analysis of stochastic direct-search
• First-order and stochastic optimization methods for machine learning
• Global convergence rate analysis of unconstrained optimization methods based on probabilistic models
• Inequalities for the $r$th Absolute Moment of a Sum of Random Variables, $1 \leqq r \leqq 2$
• Introduction to Derivative-Free Optimization
• On the efficiency of certain quasi-random sequences of points in evaluating multi-dimensional integrals
• On the Global Convergence of Derivative-Free Methods for Unconstrained Optimization
• Probability
• Random gradient-free minimization of convex functions
• Stochastic analysis of an adaptive cubic regularization method under inexact gradient evaluations and dynamic Hessian accuracy
• Stochastic derivative-free optimization using a trust region framework
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• Stochastic mesh adaptive direct search for blackbox optimization using probabilistic estimates
• Stochastic optimization using a trust-region method and random models
• Stochastic Zeroth-Order Riemannian Derivative Estimation and Optimization
• The Exact Constant in the Rosenthal Inequality for Random Variables with Mean Zero
• Trust-region methods for the derivative-free optimization of nonsmooth black-box functions
• Worst case complexity of direct search

Cited in

(2)

• Complexity guarantees for nonconvex Newton-MR under inexact Hessian information
• Complexity of zeroth- and first-order stochastic trust-region algorithms

This page was built for publication: Stochastic trust-region and direct-search methods: a weak tail bound condition and reduced sample sizing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6561380)