Damped Proximal Augmented Lagrangian Method for weakly-Convex Problems with Convex Constraints
Not on the map. Why?
Abstract (arXiv)
We give a damped proximal augmented Lagrangian method (DPALM) for solving problems with a weakly-convex objective and convex linear/nonlinear constraints. Instead of taking a full stepsize, DPALM adopts a damped dual stepsize to ensure the boundedness of dual iterates. We show that DPALM can produce a (near) vareps-KKT point within O(vareps-2) outer iterations if each DPALM subproblem is solved to a proper accuracy. In addition, we establish overall iteration complexity of DPALM when the objective is either a regularized smooth function or in a regularized compositional form. For the former case, DPALM achieves the complexity of widetildeOleft(varepsilon-2.5 right) to produce an varepsilon-KKT point by applying an accelerated proximal gradient (APG) method to each DPALM subproblem. For the latter case, the complexity of DPALM is widetildeOleft(varepsilon-3 right) to produce a near varepsilon-KKT point by using an APG to solve a Moreau-envelope smoothed version of each subproblem. Our outer iteration complexity and the overall complexity either generalize existing best ones from unconstrained or linear-constrained problems to convex-constrained ones, or improve over the best-known results on solving the same-structured problems. Furthermore, numerical experiments on linearly/quadratically constrained non-convex quadratic programs and linear-constrained robust nonlinear least squares are conducted to demonstrate the empirical efficiency of the proposed DPALM over several state-of-the art methods.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 38 of its 66 references that are in the map. First posted on arXiv 15 Nov 2023.
Builds on
38 of 66 references.
References · 38
- 2013Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programmingcited by 716
- 2018Stochastic model-based minimization of weakly convex functionscited by 157
- 2016Stochastic Variance Reduction for Nonconvex Optimizationcited by 143
- 2013Accelerated Gradient Methods for Nonconvex Nonlinear and Stochastic Programmingcited by 74
- 2016Efficiency of minimizing compositions of convex functions and smooth mapscited by 59
- 2018Stochastic subgradient method converges at the rate O(k-1/4) on weakly convex functionscited by 31
- 2017Proximally Guided Stochastic Subgradient Method for Nonsmooth, Nonconvex Problemscited by 30
- 2020Recent Theoretical Advances in Non-Convex Optimizationcited by 30
- 2019An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraintscited by 29
- 2017Iteration complexity of inexact augmented Lagrangian methods for constrained convex programmingcited by 21
- 2020Rate-improved Inexact Augmented Lagrangian Method for Constrained Nonconvex Optimizationcited by 21
- 2018On the Convergence Rate of Stochastic Mirror Descent for Nonsmooth Nonconvex Optimizationcited by 18
26 more
- 2018Complexity of a quadratic penalty accelerated inexact proximal point method for solving linearly constrained nonconvex composite programscited by 15
- 2018A Proximal Alternating Direction Method of Multiplier for Linearly Constrained Nonconvex Minimizationcited by 14
- 2016Structured Nonconvex and Nonsmooth Optimization: Algorithms and Iteration Complexity Analysiscited by 13
- 2020A global dual error bound and its application to the analysis of linearly constrained nonconvex optimizationcited by 13
- 2018Primal-dual stochastic gradient method for convex programs with many functional constraintscited by 12
- 2017Mirror Descent and Convex Optimization Problems With Non-Smooth Inequality Constraintscited by 10
- 2021Moreau Envelope Augmented Lagrangian Method for Nonconvex Optimization with Linear Constraintscited by 10
- 2017First-order methods for constrained convex programming based on linearized augmented Lagrangian functioncited by 9
- 2017Natasha: Faster Non-Convex Stochastic Optimization Via Strongly Non-Convex Parametercited by 8
- 2015Complexity of first order inexact Lagrangian and penalty methods for conic convex programmingcited by 7
- 2016On the non-ergodic convergence rate of an inexact augmented Lagrangian framework for composite convex programmingcited by 7
- 2018Iteration complexity of first-order augmented Lagrangian methods for convex conic programmingcited by 7
- 2015A Simple Parallel Algorithm with an O(1/t) Convergence Rate for General Convex Programscited by 6
- 2016Decomposing Linearly Constrained Nonconvex Problems by a Proximal Primal Dual Approach: Algorithms, Convergence, and Applicationscited by 6
- 2020Iteration-complexity of an inexact proximal accelerated augmented Lagrangian method for solving linearly constrained smooth nonconvex composite optimization problemscited by 6
- 2020Iteration-complexity of a proximal augmented Lagrangian method for solving nonconvex composite optimization problems with nonlinear convex constraintscited by 6
- 2015Adaptive inexact fast augmented Lagrangian methods for constrained convex optimizationcited by 5
- 2017Iteration-complexity of a Jacobi-type non-Euclidean ADMM for multi-block linearly constrained nonconvex programscited by 5
- 2020First-order methods for problems with O(1) functional constraints can have almost the same convergence rate as for unconstrained problemscited by 4
- 2017Convergence rate bounds for a proximal ADMM with over-relaxation stepsize parameter for solving nonconvex linearly constrained problemscited by 3
- 2021An Accelerated Inexact Dampened Augmented Lagrangian Method for Linearly-Constrained Nonconvex Composite Optimization Problemscited by 3
- 2013An Inexact Proximal Path-Following Algorithm for Constrained Convex Minimizationcited by 2
- 2018Primal-Dual Frank-Wolfe for Constrained Stochastic Programs with Convex and Non-convex Objectivescited by 2
- 2018Solving Non-smooth Constrained Programs with Lower Complexity than O(1/varepsilon): A Primal-Dual Homotopy Smoothing Approachcited by 2
- 2014A Primal-Dual Algorithmic Framework for Constrained Convex Minimizationcited by 1
- 2018Accelerated Stochastic Algorithms for Nonconvex Finite-sum and Multi-block Optimizationcited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.