Complexity of an inexact proximal-point penalty method for constrained smooth non-convex optimization
From MaRDI portal
Publication:2125072
Abstract: In this paper, an inexact proximal-point penalty method is studied for constrained optimization problems, where the objective function is non-convex, and the constraint functions can also be non-convex. The proposed method approximately solves a sequence of subproblems, each of which is formed by adding to the original objective function a proximal term and quadratic penalty terms associated to the constraint functions. Under a weak-convexity assumption, each subproblem is made strongly convex and can be solved effectively to a required accuracy by an optimal gradient-based method. The computational complexity of the proposed method is analyzed separately for the cases of convex constraint and non-convex constraint. For both cases, the complexity results are established in terms of the number of proximal gradient steps needed to find an -stationary point. When the constraint functions are convex, we show a complexity result of to produce an -stationary point under the Slater's condition. When the constraint functions are non-convex, the complexity becomes if a non-singularity condition holds on constraints and otherwise if a feasible initial solution is available.
Recommendations
- Complexity of a quadratic penalty accelerated inexact proximal point method for solving linearly constrained nonconvex composite programs
- Worst-case evaluation complexity of a quadratic penalty method for nonconvex optimization
- Constrained nonconvex nonsmooth optimization via proximal bundle method
- On the complexity of an augmented Lagrangian method for nonconvex optimization
- A stochastic primal-dual method for a class of nonconvex constrained optimization
Cites work
- A Continuously Differentiable Exact Penalty Function for Nonlinear Programming Problems with Inequality Constraints
- A Globally Convergent Linearly Constrained Lagrangian Method for Nonlinear Optimization
- A proximal alternating direction method of multiplier for linearly constrained nonconvex minimization
- A recursive quadratic programming algorithm that uses differentiable exact penalty functions
- A simple parallel algorithm with an \(O(1/t)\) convergence rate for general convex programs
- A single-phase, proximal path-following framework
- Accelerated gradient methods for nonconvex nonlinear and stochastic programming
- Adaptive augmented Lagrangian methods: algorithms and practical numerical experience
- Algorithms for stochastic optimization with function or expectation constraints
- An adaptive accelerated proximal gradient method and its homotopy continuation for sparse optimization
- An Exact Penalization Viewpoint of Constrained Optimization
- An exact penalty function method with global convergence properties for nonlinear programming problems
- An inexact proximal path-following algorithm for constrained convex minimization
- Augmented Lagrangians with constrained subproblems and convergence to second-order stationary points
- Barrier subgradient method
- Complexity and performance of an augmented Lagrangian algorithm
- Complexity of a quadratic penalty accelerated inexact proximal point method for solving linearly constrained nonconvex composite programs
- Complexity of first-order inexact Lagrangian and penalty methods for conic convex programming
- Complexity of proximal augmented Lagrangian for nonconvex optimization with nonlinear equality constraints
- Composite self-concordant minimization
- Convergence rate bounds for a proximal ADMM with over-relaxation stepsize parameter for solving nonconvex linearly constrained problems
- Corrigendum to: ``On the complexity of finding first-order critical points in constrained nonlinear optimization
- Efficiency of minimizing compositions of convex functions and smooth maps
- Global convergence of ADMM in nonconvex nonsmooth optimization
- Global minimization using an augmented Lagrangian method with variable lower-level constraints
- Gradient methods for minimizing composite functions
- scientific article; zbMATH DE number 1266748 (Why is no real title available?)
- Introductory lectures on convex optimization. A basic course.
- Iteration-complexity of first-order penalty methods for convex programming
- Local convergence of exact and inexact augmented Lagrangian methods under the second-order sufficient optimality condition
- Mirror descent and convex optimization problems with non-smooth inequality constraints
- NC-OPT
- On the complexity of finding first-order critical points in constrained nonlinear optimization
- On the Convergence of a Sequential Penalty Function Method for Constrained Minimization
- On the Convergence of Successive Linear-Quadratic Programming Algorithms
- On the evaluation complexity of composite function minimization with applications to nonconvex nonlinear programming
- On the learnability and design of output codes for multiclass problems
- Optimality condition and complexity analysis for linearly-constrained optimization without differentiability on the boundary
- Penalty methods with stochastic approximation for stochastic nonlinear programming
- Perturbed proximal primal-dual algorithm for nonconvex nonsmooth optimization
- Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
- Proximal alternating penalty algorithms for nonsmooth constrained convex optimization
- Proximally guided stochastic subgradient method for nonsmooth, nonconvex problems
- Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
- Stochastic model-based minimization of weakly convex functions
- Structured nonconvex and nonsmooth optimization: algorithms and iteration complexity analysis
Cited in
(24)- Complexity of proximal augmented Lagrangian for nonconvex optimization with nonlinear equality constraints
- A stochastic primal-dual method for a class of nonconvex constrained optimization
- Lagrangian-penalization algorithm for constrained optimization and variational inequalities
- Complexity of Partially Separable Convexly Constrained Optimization with Non-Lipschitzian Singularities
- Ghost penalties in nonconvex constrained optimization: diminishing stepsizes and iteration complexity
- First-order methods for problems with \(O(1)\) functional constraints can have almost the same convergence rate as for unconstrained problems
- Complexity of a quadratic penalty accelerated inexact proximal point method for solving linearly constrained nonconvex composite programs
- Iteration Complexity of an Inner Accelerated Inexact Proximal Augmented Lagrangian Method Based on the Classical Lagrangian Function
- Worst-case evaluation complexity of a quadratic penalty method for nonconvex optimization
- Stochastic inexact augmented Lagrangian method for nonconvex expectation constrained optimization
- Dual descent augmented Lagrangian method and alternating direction method of multipliers
- Complexity of finite-sum optimization with nonsmooth composite functions and non-Lipschitz regularization
- A proximal augmented Lagrangian method for linearly constrained nonconvex composite optimization problems
- Stochastic nested primal-dual method for nonconvex constrained composition optimization
- Game-theoretic multi-agent motion planning in a mixed environment
- Stochastic optimization over proximally smooth sets
- Variance-reduced first-order methods for deterministically constrained stochastic nonconvex optimization with strong convergence guarantees
- Complexity analysis of inexact cubic-regularized primal-dual methods for finding second-order stationary points
- A two-phase stochastic momentum-based algorithm for nonconvex expectation-constrained optimization
- Convergence rate of inexact augmented Lagrangian method with practical relative error criterion for composite convex programming
- Complexity of linearized quadratic penalty for optimization with nonlinear equality constraints
- A SPIDER-type stochastic subgradient method for expectation-constrained nonconvex nonsmooth optimization
- An adaptive parameter-free and projection-free restarting level set method for constrained convex optimization under the error bound condition
- Survey on first-order algorithms for solving functional constrained optimization problems
This page was built for publication: Complexity of an inexact proximal-point penalty method for constrained smooth non-convex optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2125072)
