Complexity and global rates of trust-region methods based on probabilistic models
From MaRDI portal
Publication:4555983
DOI10.1093/imanum/drx043zbMath1477.65093OpenAlexW2795347428MaRDI QIDQ4555983
Zaikun Zhang, C. W. Royer, Serge Gratton, Luis Nunes Vicente
Publication date: 23 November 2018
Published in: IMA Journal of Numerical Analysis (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1093/imanum/drx043
Numerical mathematical programming methods (65K05) Abstract computational complexity for mathematical programming problems (90C60) Nonconvex programming, global optimization (90C26) Derivative-free methods and methods using generalized derivatives (90C56)
Related Items
A fully stochastic second-order trust region method, A Stochastic Levenberg--Marquardt Method Using Random Models with Complexity Results, Stochastic Trust-Region Methods with Trust-Region Radius Depending on Probabilistic Models, Global Linear Convergence of Evolution Strategies on More than Smooth Strongly Convex Functions, Coupled Learning Enabled Stochastic Programming with Endogenous Uncertainty, Scalable subspace methods for derivative-free nonlinear least-squares optimization, An adaptive stochastic sequential quadratic programming with differentiable exact augmented Lagrangians, Inequality constrained stochastic nonlinear optimization via active-set sequential quadratic programming, Direct Search Based on Probabilistic Descent in Reduced Spaces, Globally Convergent Multilevel Training of Deep Residual Networks, Newton-type methods for non-convex optimization under inexact Hessian information, Convergence of Newton-MR under Inexact Hessian Information, Trust-Region Methods for the Derivative-Free Optimization of Nonsmooth Black-Box Functions, Derivative-free optimization methods