A trust region algorithm with a worst-case iteration complexity of O( ^-3/2) for nonconvex optimization
From MaRDI portal
Publication:517288
global convergencelocal convergencenonconvex optimizationnonlinear optimizationtrust region methodsunconstrained optimizationworst-case evaluation complexityworst-case iteration complexity
Newton-type methods (49M15) Numerical methods based on nonlinear programming (49M37) Implicit function theorems; global Newton methods on manifolds (58C15) Numerical mathematical programming methods (65K05) Numerical optimization and variational techniques (65K10) Complexity and performance of numerical algorithms (65Y20) Analysis of algorithms and problem complexity (68Q25) Nonlinear programming (90C30) Abstract computational complexity for mathematical programming problems (90C60)
Recommendations
- Trust-region Newton-CG with strong second-order complexity guarantees for nonconvex optimization
- An inexact regularized Newton framework with a worst-case iteration complexity of \(\mathscr{O}(\varepsilon^{-3/2})\) for nonconvex optimization
- Worst-Case Complexity of TRACE with Inexact Subproblem Solutions for Nonconvex Smooth Optimization
- A trust region method for finding second-order stationarity in linearly constrained nonconvex optimization
- Worst-case evaluation complexity and optimality of second-order methods for nonconvex smooth optimization
Cites work
- Adaptive cubic regularisation methods for unconstrained optimization. I: Motivation, convergence and numerical results
- Adaptive cubic regularisation methods for unconstrained optimization. II: Worst-case function- and derivative-evaluation complexity
- Affine conjugate adaptive Newton methods for nonlinear elastomechanics
- Computing a Trust Region Step
- Cubic regularization of Newton method and its global performance
- scientific article; zbMATH DE number 1818892 (Why is no real title available?)
- scientific article; zbMATH DE number 5359577 (Why is no real title available?)
- scientific article; zbMATH DE number 852532 (Why is no real title available?)
- scientific article; zbMATH DE number 5060482 (Why is no real title available?)
- Introductory lectures on convex optimization. A basic course.
- Nonlinear optimization.
- Nonlinear Programming
- On the complexity of steepest descent, Newton's and regularized Newton's methods for nonconvex unconstrained optimization problems
- Trust Region Methods
Cited in
(69)- Concise complexity analyses for trust region methods
- Cubic-regularization counterpart of a variable-norm trust-region method for unconstrained minimization
- On the use of the energy norm in trust-region and adaptive cubic regularization subproblems
- On the worst-case evaluation complexity of non-monotone line search algorithms
- A line-search algorithm inspired by the adaptive cubic regularization framework and complexity analysis
- Structured nonconvex and nonsmooth optimization: algorithms and iteration complexity analysis
- Second-order optimality and beyond: characterization and evaluation complexity in convexly constrained nonlinear optimization
- Optimality of orders one to three and beyond: characterization and evaluation complexity in constrained nonconvex optimization
- A reduced-space line-search method for unconstrained optimization via random descent directions
- Regional complexity analysis of algorithms for nonconvex smooth optimization
- A generalized worst-case complexity analysis for non-monotone line searches
- On large-scale unconstrained optimization and arbitrary regularization
- On complexity and convergence of high-order coordinate descent algorithms for smooth nonconvex box-constrained minimization
- A cubic regularization of Newton's method with finite difference Hessian approximations
- An active set trust-region method for bound-constrained optimization
- On the use of third-order models with fourth-order regularization for unconstrained optimization
- Newton-type methods for non-convex optimization under inexact Hessian information
- A decoupled first/second-order steps technique for nonconvex nonlinear unconstrained optimization with improved complexity bounds
- A Newton-CG algorithm with complexity guarantees for smooth unconstrained optimization
- Large-scale unconstrained optimization using separable cubic modeling and matrix-free subspace minimization
- Optimality condition and complexity analysis for linearly-constrained optimization without differentiability on the boundary
- Convergence and evaluation-complexity analysis of a regularized tensor-Newton method for solving nonlinear least-squares problems
- A Newton-like method with mixed factorizations and cubic regularization for unconstrained minimization
- On High-order Model Regularization for Constrained Optimization
- A Newton-based method for nonconvex optimization with fast evasion of saddle points
- Universal Regularization Methods: Varying the Power, the Smoothness and the Accuracy
- \texttt{trlib}: a vector-free implementation of the GLTR method for iterative solution of the trust region problem
- ARC\(_q\): a new adaptive regularization by cubics
- On regularization and active-set methods with complexity for constrained optimization
- Complexity analysis of second-order line-search algorithms for smooth nonconvex optimization
- Complexity analysis of a trust funnel algorithm for equality constrained optimization
- Accelerated regularized Newton methods for minimizing composite convex functions
- Stochastic nested variance reduction for nonconvex optimization
- Optimization with momentum: dynamical, control-theoretic, and symplectic perspectives
- On high-order model regularization for multiobjective optimization
- Nonlinear stepsize control algorithms: complexity bounds for first- and second-order optimality
- A proximal quasi-Newton trust-region method for nonsmooth regularized optimization
- A note on the worst-case complexity of nonlinear stepsize control methods for convex smooth unconstrained optimization
- Escaping strict saddle points of the Moreau envelope in nonsmooth optimization
- A trust region method for finding second-order stationarity in linearly constrained nonconvex optimization
- Second-order guarantees of distributed gradient algorithms
- Trust-region methods for the derivative-free optimization of nonsmooth black-box functions
- On the complexity of an inexact restoration method for constrained optimization
- A concise second-order complexity analysis for unconstrained optimization using high-order regularized models
- Stochastic variance-reduced cubic regularization methods
- Iteration and evaluation complexity for the minimization of functions whose computation is intrinsically inexact
- The use of quadratic regularization with a cubic descent condition for unconstrained optimization
- Regularized Newton methods for minimizing functions with Hölder continuous hessians
- Trust-region Newton-CG with strong second-order complexity guarantees for nonconvex optimization
- An inexact regularized Newton framework with a worst-case iteration complexity of \(\mathscr{O}(\varepsilon^{-3/2})\) for nonconvex optimization
- Worst-Case Complexity of TRACE with Inexact Subproblem Solutions for Nonconvex Smooth Optimization
- Complexity analysis of interior-point methods for second-order stationary points of nonlinear semidefinite optimization problems
- Decentralized nonconvex optimization with guaranteed privacy and accuracy
- 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
- Convergence Properties of an Objective-Function-Free Optimization Regularization Algorithm, Including an \(\boldsymbol{\mathcal{O}(\epsilon^{-3/2})}\) Complexity Bound
- A Newton-CG Based Augmented Lagrangian Method for Finding a Second-Order Stationary Point of Nonconvex Equality Constrained Optimization with Complexity Guarantees
- A proximal trust-region method for nonsmooth optimization with inexact function and gradient evaluations
- A deterministic gradient-based approach to avoid saddle points
- A Newton-CG based barrier-augmented Lagrangian method for general nonconvex conic optimization
- Trust region-type method under inexact gradient and inexact Hessian with convergence analysis
- Hessian barrier algorithms for non-convex conic optimization
- Homogeneous second-order descent framework: a fast alternative to Newton-type methods
- Beyond nonconvexity: a universal trust-region method with new analyses
- Yet another fast variant of Newton's method for nonconvex optimization
- Riemannian trust-region methods for strict saddle functions with complexity guarantees
- Universal heavy-ball method for nonconvex optimization under Hölder continuous Hessians
- Efficiently escaping saddle points in bilevel optimization
- Regularized methods via cubic model subspace minimization for nonconvex optimization
This page was built for publication: A trust region algorithm with a worst-case iteration complexity of \(\mathcal{O}(\epsilon ^{-3/2})\) for nonconvex optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q517288)
