An efficient adaptive accelerated inexact proximal point method for solving linearly constrained nonconvex composite problems
From MaRDI portal
Publication:2181594
DOI10.1007/s10589-020-00188-wzbMath1443.90282arXiv1812.06352MaRDI QIDQ2181594
Renato D. C. Monteiro, Jefferson G. Melo, WeiWei Kong
Publication date: 19 May 2020
Published in: Computational Optimization and Applications (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1812.06352
proximal point method; quadratic penalty method; nonconvex program; iteration-complexity; first-order accelerated methods
90C60: Abstract computational complexity for mathematical programming problems
90C26: Nonconvex programming, global optimization
90C30: Nonlinear programming
65K10: Numerical optimization and variational techniques
47J22: Variational and other types of inclusions
Related Items
An Accelerated Inexact Proximal Point Method for Solving Nonconvex-Concave Min-Max Problems, Iteration Complexity of an Inner Accelerated Inexact Proximal Augmented Lagrangian Method Based on the Classical Lagrangian Function, 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, Extrapolated smoothing descent algorithm for constrained nonconvex and nonsmooth composite problems, Accelerated inexact composite gradient methods for nonconvex spectral optimization problems
Uses Software
Cites Work
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- Accelerated gradient methods for nonconvex nonlinear and stochastic programming
- An adaptive accelerated first-order method for convex optimization
- Adaptive inexact fast augmented Lagrangian methods for constrained convex optimization
- Introductory lectures on convex optimization. A basic course.
- A hybrid approximate extragradient-proximal point algorithm using the enlargement of a maximal monotone operator
- Proximal alternating penalty algorithms for nonsmooth constrained convex optimization
- Iteration-complexity of first-order penalty methods for convex programming
- A FISTA-type accelerated gradient algorithm for solving smooth nonconvex composite optimization problems
- Generalized uniformly optimal methods for nonlinear programming
- Efficiency of minimizing compositions of convex functions and smooth maps
- Cubic regularization of Newton method and its global performance
- An Accelerated Hybrid Proximal Extragradient Method for Convex Optimization and Its Implications to Second-Order Methods
- A First-Order Augmented Lagrangian Method for Compressed Sensing
- A First-Order Smoothed Penalty Method for Compressed Sensing
- On the Complexity of Steepest Descent, Newton's and Regularized Newton's Methods for Nonconvex Unconstrained Optimization Problems
- Accelerating Block-Decomposition First-Order Methods for Solving Composite Saddle-Point and Two-Player Nash Equilibrium Problems
- An Accelerated HPE-Type Algorithm for a Class of Composite Convex-Concave Saddle-Point Problems
- Monotone Operators and the Proximal Point Algorithm
- Efficient Learning with a Family of Nonconvex Regularizers by Redistributing Nonconvexity
- Accelerated Methods for NonConvex Optimization
- An accelerated non-Euclidean hybrid proximal extragradient-type algorithm for convex–concave saddle-point problems
- First-Order Methods in Optimization
- Iteration-Complexity of a Newton Proximal Extragradient Method for Monotone Variational Inequalities and Inclusion Problems
- On the Nonergodic Convergence Rate of an Inexact Augmented Lagrangian Framework for Composite Convex Programming
- Complexity of a Quadratic Penalty Accelerated Inexact Proximal Point Method for Solving Linearly Constrained Nonconvex Composite Programs
- Optimal Primal-Dual Methods for a Class of Saddle Point Problems
- Iteration-complexity of first-order augmented Lagrangian methods for convex programming
