On the nonergodic convergence rate of an inexact augmented Lagrangian framework for composite convex programming
From MaRDI portal
Publication:5219732
Abstract: In this paper, we consider the linearly constrained composite convex optimization problem, whose objective is a sum of a smooth function and a possibly nonsmooth function. We propose an inexact augmented Lagrangian (IAL) framework for solving the problem. The stopping criterion used in solving the augmented Lagrangian (AL) subproblem in the proposed IAL framework is weaker and potentially much easier to check than the one used in most of the existing IAL frameworks/methods. We analyze the global convergence and the non-ergodic convergence rate of the proposed IAL framework.
Recommendations
- An inexact proximal augmented Lagrangian framework with arbitrary linearly convergent inner solver for composite convex optimization
- On the convergence of inexact augmented Lagrangian methods for problems with convex constraints
- An accelerated inexact dampened augmented Lagrangian method for linearly-constrained nonconvex composite optimization problems
- Iteration complexity of inexact augmented Lagrangian methods for constrained convex programming
- An accelerated augmented Lagrangian method for linearly constrained convex programming with the rate of convergence \(O\left({1/{k^2}} \right)\)
Cites work
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- A highly efficient semismooth Newton augmented Lagrangian method for solving lasso problems
- A practical relative error criterion for augmented Lagrangians
- An efficient augmented Lagrangian method with applications to total variation minimization
- An Iterative Regularization Method for Total Variation-Based Image Restoration
- Analysis on a superlinearly convergent augmented Lagrangian method
- Augmented Lagrangians and Applications of the Proximal Point Algorithm in Convex Programming
- Bregman Iterative Algorithms for \ell₁-Minimization with Applications to Compressed Sensing
- Complexity bounds for primal-dual methods minimizing the model of objective function
- Complexity of first-order inexact Lagrangian and penalty methods for conic convex programming
- Computational complexity of inexact gradient augmented Lagrangian methods: application to constrained MPC
- Conditional gradient algorithms for norm-regularized smooth convex optimization
- Conditional gradient sliding for convex optimization
- Convergence Rate Analysis of Nonquadratic Proximal Methods for Convex and Linear Programming
- Error bounds and convergence analysis of feasible descent methods: A general approach
- Error forgetting of Bregman iteration
- First-order methods of smooth convex optimization with inexact oracle
- Gradient Convergence in Gradient methods with Errors
- Gradient methods for minimizing composite functions
- Gradient sliding for composite optimization
- scientific article; zbMATH DE number 1818892 (Why is no real title available?)
- scientific article; zbMATH DE number 3850830 (Why is no real title available?)
- scientific article; zbMATH DE number 3309655 (Why is no real title available?)
- Iteration complexity analysis of dual first-order methods for conic convex programming
- Iteration-complexity of first-order augmented Lagrangian methods for convex programming
- Multiplier and gradient methods
- Newton’s Method for Optimization Problems with Equality Constraints
- Non-asymptotic convergence analysis of inexact gradient methods for machine learning without strong convexity
- Scalable robust matrix recovery: Frank-Wolfe meets proximal methods
- SDPNAL+: a majorized semismooth Newton-CG augmented Lagrangian method for semidefinite programming with nonnegative constraints
- Smooth minimization of non-smooth functions
- The multiplier method of Hestenes and Powell applied to convex programming
- The Split Bregman Method for L1-Regularized Problems
Cited in
(30)- Decomposition and discrete approximation methods for solving two-stage distributionally robust optimization problems
- An inexact proximal augmented Lagrangian framework with arbitrary linearly convergent inner solver for composite convex optimization
- Inertial accelerated primal-dual methods for linear equality constrained convex optimization problems
- An efficient adaptive accelerated inexact proximal point method for solving linearly constrained nonconvex composite problems
- Iteration complexity of inexact augmented Lagrangian methods for constrained convex programming
- An ADMM-based location-allocation algorithm for nonconvex constrained multi-source Weber problem under gauge
- Scalable semidefinite programming
- A novel augmented Lagrangian method of multipliers for optimization with general inequality constraints
- Iteration Complexity of an Inner Accelerated Inexact Proximal Augmented Lagrangian Method Based on the Classical Lagrangian Function
- Accelerated First-Order Methods for Convex Optimization with Locally Lipschitz Continuous Gradient
- An adaptive superfast inexact proximal augmented Lagrangian method for smooth nonconvex composite optimization problems
- An accelerated inexact dampened augmented Lagrangian method for linearly-constrained nonconvex composite optimization problems
- A new Lagrangian-based first-order method for nonconvex constrained optimization
- A linear algebra perspective on the random multi-block ADMM: the QP case
- Iteration-Complexity of First-Order Augmented Lagrangian Methods for Convex Conic Programming
- Inexact and stochastic generalized conditional gradient with augmented Lagrangian and proximal step
- Local properties and augmented Lagrangians in fully nonconvex composite optimization
- A proximal augmented Lagrangian method for linearly constrained nonconvex composite optimization problems
- Seeking consensus on subspaces in federated principal component analysis
- Inertial accelerated augmented Lagrangian algorithms with scaling coefficients to solve exactly and inexactly linearly constrained convex optimization problems
- An inexact linearized augmented Lagrangian method for the linearly composite convex programming
- Global convergence analysis of the power proximal point and augmented Lagrangian method
- Efficient low rank matrix recovery with flexible group sparse regularization
- A smoothed augmented Lagrangian framework for convex optimization with nonsmooth constraints
- Convergence rate of inexact augmented Lagrangian method with practical relative error criterion for composite convex programming
- Splitting the conditional gradient algorithm
- A -inertial ADMM for efficient and stable nonconvex optimization
- A SPIDER-type stochastic subgradient method for expectation-constrained nonconvex nonsmooth optimization
- Accelerated linearized alternating direction method of multipliers with Nesterov extrapolation
- The augmented Lagrangian methods: overview and recent advances
This page was built for publication: On the nonergodic convergence rate of an inexact augmented Lagrangian framework for composite convex programming
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5219732)
