ADMM for multiaffine constrained optimization
From MaRDI portal
Abstract: We expand the scope of the alternating direction method of multipliers (ADMM). Specifically, we show that ADMM, when employed to solve problems with multiaffine constraints that satisfy certain verifiable assumptions, converges to the set of constrained stationary points if the penalty parameter in the augmented Lagrangian is sufficiently large. When the Kurdyka-L{}ojasiewicz (K-L{}) property holds, this is strengthened to convergence to a single constrained stationary point. Our analysis applies under assumptions that we have endeavored to make as weak as possible. It applies to problems that involve nonconvex and/or nonsmooth objective terms, in addition to the multiaffine constraints that can involve multiple (three or more) blocks of variables. To illustrate the applicability of our results, we describe examples including nonnegative matrix factorization, sparse learning, risk parity portfolio selection, nonconvex formulations of convex problems, and neural network training. In each case, our ADMM approach encounters only subproblems that have closed-form solutions.
Recommendations
- Convergence analysis of alternating direction method of multipliers for a family of nonconvex problems
- Global convergence of ADMM in nonconvex nonsmooth optimization
- Convergence of ADMM for multi-block nonconvex separable optimization models
- Convergence of ADMM for optimization problems with nonseparable nonconvex objective and linear constraints
- Inertial alternating direction method of multipliers for non-convex non-smooth optimization
Cites work
- A convergent 3-block semi-proximal ADMM for convex minimization problems with one strongly convex block
- A convergent 3-block semiproximal alternating direction method of multipliers for conic programming with 4-type constraints
- A dual algorithm for the solution of nonlinear variational problems via finite element approximation
- A majorized ADMM with indefinite proximal terms for linearly constrained convex composite optimization
- A nonlinear programming algorithm for solving semidefinite programs via low-rank factorization
- A note on the alternating direction method of multipliers
- A note on the convergence of ADMM for linearly constrained convex optimization problems
- A Really Simple Elementary Proof of the Uniform Boundedness Theorem
- A Schur complement based semi-proximal ADMM for convex quadratic conic programming and extensions
- A three-operator splitting scheme and its optimization applications
- Adapting regularized low-rank models for parallel architectures
- Alternating direction method of multipliers for real and complex polynomial optimization models
- An algorithm twisted from generalized ADMM for multi-block separable convex minimization models
- An alternating direction algorithm for matrix completion with nonnegative factors
- An efficient inexact symmetric Gauss-Seidel based majorized ADMM for high-dimensional convex composite conic programming
- Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture
- Complete Dictionary Recovery Over the Sphere II: Recovery by Riemannian Trust-Region Method
- Convergence analysis of alternating direction method of multipliers for a family of nonconvex problems
- Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
- Cubic regularization of Newton method and its global performance
- Directional derivative of the marginal function in nonlinear programming
- Distributed optimization and statistical learning via the alternating direction method of multipliers
- Global convergence of ADMM in nonconvex nonsmooth optimization
- Global convergence of splitting methods for nonconvex composite optimization
- Global convergence of unmodified 3-block ADMM for a class of convex minimization problems
- Hankel matrix rank minimization with applications to system identification and realization
- scientific article; zbMATH DE number 3574917 (Why is no real title available?)
- Implications of the constant rank constraint qualification
- Improved approximation algorithms for maximum cut and satisfiability problems using semidefinite programming
- Improved proximal ADMM with partially parallel splitting for multi-block separable convex programming
- Learning the parts of objects by non-negative matrix factorization
- Linearized alternating direction method with parallel splitting and adaptive penalty for separable convex programs in machine learning
- Nonconvex Lagrangian-based optimization: monitoring schemes and global convergence
- On the convergence properties of a majorized alternating direction method of multipliers for linearly constrained convex optimization problems with coupled objective functions
- On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators
- On the Global Linear Convergence of the ADMM with MultiBlock Variables
- On the Linear Convergence of the ADMM in Decentralized Consensus Optimization
- On the sublinear convergence rate of multi-block ADMM
- Online learning for matrix factorization and sparse coding
- Parallel multi-block ADMM with \(o(1/k)\) convergence
- Primal-dual optimization algorithms over Riemannian manifolds: an iteration complexity analysis
- Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
- Reducibility among combinatorial problems
- Robust principal component analysis?
- Smooth minimization of non-smooth functions
- Splitting Algorithms for the Sum of Two Nonlinear Operators
- Structured nonconvex and nonsmooth optimization: algorithms and iteration complexity analysis
- The direct extension of ADMM for multi-block convex minimization problems is not necessarily convergent
- Understanding the convergence of the alternating direction method of multipliers: theoretical and computational perspectives
- Uniqueness of DRS as the 2 operator resolvent-splitting and impossibility of 3 operator resolvent-splitting
- Variational Analysis
Cited in
(24)- Preconditioned ADMM for a class of bilinear programming problems
- On the conditions for the finite termination of ADMM and its applications to SOS polynomials feasibility problems
- Global attractor and limit points for nonsmooth ADMM
- Imitation learning of stabilizing policies for nonlinear systems
- Passivity-based analysis of the ADMM algorithm for constraint-coupled optimization
- Solving blind ptychography effectively via linearized alternating direction method of multipliers
- Improving ADMMs for solving doubly nonnegative programs through dual factorization
- Efficient differentiable quadratic programming layers: an ADMM approach
- ADMM for Exploiting Structure in MPC Problems
- scientific article; zbMATH DE number 7626714 (Why is no real title available?)
- Fast and Effective Multiframe-Task Parameter Assignment Via Concave Approximations of Demand
- A splitting scheme for flip-free distortion energies
- Multicomposite nonconvex optimization for training deep neural networks
- A proximal alternating direction method of multiplier for linearly constrained nonconvex minimization
- scientific article; zbMATH DE number 7164723 (Why is no real title available?)
- Optimization Algorithms for Graph Laplacian Estimation via ADMM and MM
- Self equivalence of the alternating direction method of multipliers
- ADMM and Non-convex Variational Problems
- Global convergence in learning fully-connected ReLU networks via un-rectifying based on the augmented Lagrangian approach
- A relaxed alternating direction method of multipliers for separable nonconvex minimization problems
- A robust shifted proper orthogonal decomposition: proximal methods for decomposing flows with multiple transports
- A three-step framework for noisy image segmentation in brain MRI
- Using filter methods to guide convergence for ADMM, with applications to nonnegative matrix factorization problems
- A Relaxed Gradient Step Denoiser for Splitting Methods in Poisson Inverse Problems
This page was built for publication: ADMM for multiaffine constrained optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5210740)
