An inexact regularized Newton framework with a worst-case iteration complexity of $ {\mathscr O}(\varepsilon^{-3/2}) $ for nonconvex optimization

DOI10.1093/imanum/dry022zbMath1464.65062arXiv1708.00475OpenAlexW2963386167MaRDI QIDQ5854356

Mohammadreza Samadi, Daniel P. Robinson, Frank E. Curtis

Publication date: 16 March 2021

Published in: IMA Journal of Numerical Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1708.00475

zbMATH Keywords

unconstrained optimizationinexact Newton methodsnonlinear optimizationnonconvex optimizationworst-case iteration complexityworst-case evaluation complexity

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10)

Related Items

Worst-Case Complexity of TRACE with Inexact Subproblem Solutions for Nonconvex Smooth Optimization, A Newton-CG Based Barrier Method for Finding a Second-Order Stationary Point of Nonconvex Conic Optimization with Complexity Guarantees, A nonlinear conjugate gradient method with complexity guarantees and its application to nonconvex regression, Regional complexity analysis of algorithms for nonconvex smooth optimization, A Newton-CG algorithm with complexity guarantees for smooth unconstrained optimization, An adaptive high order method for finding third-order critical points of nonconvex optimization, Trust-Region Newton-CG with Strong Second-Order Complexity Guarantees for Nonconvex Optimization