Accelerated Inexact First-Order Methods for Solving Nonconvex Composite Optimization Problems
arXiv:2104.09685
Abstract
This thesis focuses on developing and analyzing accelerated and inexact first-order methods for solving or finding stationary points of various nonconvex composite optimization (NCO) problems. The main tools mainly come from variational and convex analysis, and the key results are in the form of iteration complexity bounds and how these bounds compare to other ones in the literature.
References in corpus (18)
- Splitting methods with variable metric for KL functions
- Complexity and performance of an Augmented Lagrangian algorithm
- Near-Optimal Algorithms for Minimax Optimization
- On the Complexity of an Augmented Lagrangian Method for Nonconvex Optimization
- Decomposing Linearly Constrained Nonconvex Problems by a Proximal Primal Dual Approach: Algorithms, Convergence, and Applications
- Efficient Algorithms for Smooth Minimax Optimization
- Catalyst Acceleration for Gradient-Based Non-Convex Optimization
- Sparse PCA with Oracle Property
- An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints
- An accelerated inexact proximal point method for solving nonconvex-concave min-max problems
- Calibrated Elastic Regularization in Matrix Completion
- Iteration complexity of first-order augmented Lagrangian methods for convex conic programming
- Iteration-complexity of an inexact proximal accelerated augmented Lagrangian method for solving linearly constrained smooth nonconvex composite optimization problems
- A global dual error bound and its application to the analysis of linearly constrained nonconvex optimization
- Rate-improved Inexact Augmented Lagrangian Method for Constrained Nonconvex Optimization
- A Doubly Accelerated Inexact Proximal Point Method for Nonconvex Composite Optimization Problems
- Lower Bounds for Smooth Nonconvex Finite-Sum Optimization
- A FISTA-type accelerated gradient algorithm for solving smooth nonconvex composite optimization problems