Adaptive cubic regularisation methods for unconstrained optimization. II: Worst-case function- and derivative-evaluation complexity
From MaRDI portal
(Redirected from Publication:652287)
nonlinear optimizationunconstrained optimizationglobal rate of convergenceNewton's methodtrust-region methodscubic regularizationglobal complexity bounds
Numerical mathematical programming methods (65K05) Analysis of algorithms and problem complexity (68Q25) Nonlinear programming (90C30) Numerical methods based on nonlinear programming (49M37) Abstract computational complexity for mathematical programming problems (90C60) Newton-type methods (49M15) Implicit function theorems; global Newton methods on manifolds (58C15)
Recommendations
- Adaptive cubic regularisation methods for unconstrained optimization. I: Motivation, convergence and numerical results
- Evaluation complexity of adaptive cubic regularization methods for convex unconstrained optimization
- ARC\(_q\): a new adaptive regularization by cubics
- On the use of iterative methods in cubic regularization for unconstrained optimization
- Complexity bounds for second-order optimality in unconstrained optimization
Cites work
- scientific article; zbMATH DE number 3928227 (Why is no real title available?)
- scientific article; zbMATH DE number 961607 (Why is no real title available?)
- A Characterization of Superlinear Convergence and Its Application to Quasi-Newton Methods
- A recursive Formula-trust-region method for bound-constrained nonlinear optimization
- Accelerating the cubic regularization of Newton's method on convex problems
- Adaptive cubic regularisation methods for unconstrained optimization. I: Motivation, convergence and numerical results
- Affine conjugate adaptive Newton methods for nonlinear elastomechanics
- Cubic regularization of Newton method and its global performance
- Introductory lectures on convex optimization. A basic course.
- Numerical Optimization
- Recursive Trust-Region Methods for Multiscale Nonlinear Optimization
- Trust Region Methods
Cited in
(only showing first 100 items - show all)- Homogeneous second-order descent framework: a fast alternative to Newton-type methods
- Evaluation complexity for nonlinear constrained optimization using unscaled KKT conditions and high-order models
- Cubic regularization methods with second-order complexity guarantee based on a new subproblem reformulation
- Beyond nonconvexity: a universal trust-region method with new analyses
- Derivative-free separable quadratic modeling and cubic regularization for unconstrained optimization
- Second-order guarantees of distributed gradient algorithms
- Convergence and evaluation-complexity analysis of a regularized tensor-Newton method for solving nonlinear least-squares problems
- Solving the cubic regularization model by a nested restarting Lanczos method
- Iteration and evaluation complexity for the minimization of functions whose computation is intrinsically inexact
- A note on the worst-case complexity of nonlinear stepsize control methods for convex smooth unconstrained optimization
- On the convergence and worst-case complexity of trust-region and regularization methods for unconstrained optimization
- Riemannian stochastic variance-reduced cubic regularized Newton method for submanifold optimization
- On large-scale unconstrained optimization and arbitrary regularization
- Fast convergence of trust-regions for non-isolated minima via analysis of CG on indefinite matrices
- On regularization and active-set methods with complexity for constrained optimization
- Finding zeros of Hölder metrically subregular mappings via globally convergent Levenberg-Marquardt methods
- On the use of third-order models with fourth-order regularization for unconstrained optimization
- Worst-case evaluation complexity of non-monotone gradient-related algorithms for unconstrained optimization
- An adaptive cubic regularization inexact-Newton method on Riemannian manifolds
- A concise second-order complexity analysis for unconstrained optimization using high-order regularized models
- Recent advances in trust region algorithms
- Nonlinear stepsize control algorithms: complexity bounds for first- and second-order optimality
- Zeroth-order nonconvex stochastic optimization: handling constraints, high dimensionality, and saddle points
- A trust region algorithm with a worst-case iteration complexity of \(\mathcal{O}(\epsilon ^{-3/2})\) for nonconvex optimization
- Worst-case evaluation complexity for unconstrained nonlinear optimization using high-order regularized models
- On the Evaluation Complexity of Constrained Nonlinear Least-Squares and General Constrained Nonlinear Optimization Using Second-Order Methods
- On the use of the energy norm in trust-region and adaptive cubic regularization subproblems
- Complexity analysis of interior point algorithms for non-Lipschitz and nonconvex minimization
- Hessian barrier algorithms for non-convex conic optimization
- A unified adaptive tensor approximation scheme to accelerate composite convex optimization
- Complexity of Partially Separable Convexly Constrained Optimization with Non-Lipschitzian Singularities
- An adaptive high order method for finding third-order critical points of nonconvex optimization
- Recent Theoretical Advances in Non-Convex Optimization
- Perseus: a simple and optimal high-order method for variational inequalities
- A note about the complexity of minimizing Nesterov's smooth Chebyshev-Rosenbrock function
- Accelerated adaptive cubic regularized quasi-Newton methods
- A second-order globally convergent direct-search method and its worst-case complexity
- Convergence of Newton-MR under inexact Hessian information
- A sequential adaptive regularisation using cubics algorithm for solving nonlinear equality constrained optimization
- Majorization-minimization-based Levenberg-Marquardt method for constrained nonlinear least squares
- On the complexity of an inexact restoration method for constrained optimization
- An adaptive cubic regularization algorithm for computing H- and Z-eigenvalues of real even-order supersymmetric tensors
- Adaptive cubic regularization methods with dynamic inexact Hessian information and applications to finite-sum minimization
- On the use of iterative methods in cubic regularization for unconstrained optimization
- Newton-MR: inexact Newton method with minimum residual sub-problem solver
- On the complexity of solving feasibility problems with regularized models
- Fast convergence to non-isolated minima: four equivalent conditions for \({\mathrm{C}^2}\) functions
- Stochastic variance-reduced cubic regularization methods
- \texttt{trlib}: a vector-free implementation of the GLTR method for iterative solution of the trust region problem
- A randomized algorithm for nonconvex minimization with inexact evaluations and complexity guarantees
- Complexity bound of trust-region methods for convex smooth unconstrained multiobjective optimization
- Riemannian adaptive regularized Newton methods with Hölder continuous Hessians
- A trust region method for finding second-order stationarity in linearly constrained nonconvex optimization
- On local nonglobal minimum of trust-region subproblem and extension
- A Newton-CG Based Augmented Lagrangian Method for Finding a Second-Order Stationary Point of Nonconvex Equality Constrained Optimization with Complexity Guarantees
- Large-scale unconstrained optimization using separable cubic modeling and matrix-free subspace minimization
- Adaptive Regularization Algorithms with Inexact Evaluations for Nonconvex Optimization
- On high-order model regularization for multiobjective optimization
- Complexity analysis of a trust funnel algorithm for equality constrained optimization
- A decentralized smoothing quadratic regularization algorithm for composite consensus optimization with non-Lipschitz singularities
- An accelerated first-order method for non-convex optimization on manifolds
- Cubic-regularization counterpart of a variable-norm trust-region method for unconstrained minimization
- First and zeroth-order implementations of the regularized Newton method with lazy approximated Hessians
- A stochastic objective-function-free adaptive regularization method with optimal complexity
- Solving Large-Scale Cubic Regularization by a Generalized Eigenvalue Problem
- On High-order Model Regularization for Constrained Optimization
- Universal heavy-ball method for nonconvex optimization under Hölder continuous Hessians
- Super-Universal Regularized Newton Method
- Parameter-free accelerated gradient descent for nonconvex minimization
- A Riemannian dimension-reduced second-order method with application in sensor network localization
- Second-order optimality and beyond: characterization and evaluation complexity in convexly constrained nonlinear optimization
- A line-search algorithm inspired by the adaptive cubic regularization framework and complexity analysis
- Convergence Properties of an Objective-Function-Free Optimization Regularization Algorithm, Including an \(\boldsymbol{\mathcal{O}(\epsilon^{-3/2})}\) Complexity Bound
- An inexact q-order regularized proximal Newton method for nonconvex composite optimization
- Complexity analysis of second-order line-search algorithms for smooth nonconvex optimization
- On a global complexity bound of the Levenberg-marquardt method
- Cubic regularization in symmetric rank-1 quasi-Newton methods
- Optimality of orders one to three and beyond: characterization and evaluation complexity in constrained nonconvex optimization
- First-Order Methods for Nonconvex Quadratic Minimization
- Cubic overestimation and secant updating for unconstrained optimization of \(C^{2,1}\) functions
- On the complexity of a stochastic Levenberg-Marquardt method
- Subsampled cubic regularization method for finite-sum minimization
- A Newton-like method with mixed factorizations and cubic regularization for unconstrained minimization
- Evaluation complexity of adaptive cubic regularization methods for convex unconstrained optimization
- Gradient descent in the absence of global Lipschitz continuity of the gradients
- Inexact tensor methods and their application to stochastic convex optimization
- Universal Regularization Methods: Varying the Power, the Smoothness and the Accuracy
- Worst case complexity of direct search
- Two modified adaptive cubic regularization algorithms by using the nonmonotone Armijo-type line search
- Structured nonconvex and nonsmooth optimization: algorithms and iteration complexity analysis
- Worst case complexity of direct search under convexity
- A new regularized quasi-Newton algorithm for unconstrained optimization
- On the complexity of finding first-order critical points in constrained nonlinear optimization
- Concise complexity analyses for trust region methods
- The use of quadratic regularization with a cubic descent condition for unconstrained optimization
- A derivative-free trust-region algorithm for composite nonsmooth optimization
- A Newton-based method for nonconvex optimization with fast evasion of saddle points
- On the worst-case complexity of nonlinear stepsize control algorithms for convex unconstrained optimization
- Sharp worst-case evaluation complexity bounds for arbitrary-order nonconvex optimization with inexpensive constraints
- Projected adaptive cubic regularization algorithm with derivative-free filter technique for box constrained optimization
This page was built for publication: Adaptive cubic regularisation methods for unconstrained optimization. II: Worst-case function- and derivative-evaluation complexity
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q652287)
