Proximal alternating linearized minimization for nonconvex and nonsmooth problems

2013/07/25 by Jérôme Bolte, Shoham Sabach, Marc Teboulle · 135 citations
Engineering · Mathematics · Computer Science · #Sparse and Compressive Sensing Techniques #Advanced Optimization Algorithms Research #Optimization and Variational Analysis

paper · doi:10.1007/s10107-013-0701-9

Citations

• Convergence of a Block Coordinate Descent Method for Nondifferentiable Minimization
• Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward–backward splitting, and regularized Gauss–Seidel methods

Cited by

• From error bounds to the complexity of first-order descent methods for convex functions
• An exact penalty approach for optimization with nonnegative orthogonality constraints
• Riemannian proximal gradient methods
• CADMM-Prox: A Bi-level Consensus ADMM for Non-smooth Non-convex Distributed Consensus Optimization
• Learning Doubly Sparse Explicitly Conditioned Transforms
• Global Convergence of Inexact Augmented Lagrangian Method for Zero-One Composite Optimization
• Kurdyka-Łojasiewicz exponent via inf-projection
• An Efficient and Globally Convergent Algorithm for ℓ_p,q-ℓ_r Model in Group Sparse Optimization
• Clustering with feature selection using alternating minimization, Application to computational biology
• Efficient numerical methods for computing the stationary states of phase field crystal models
• NetREX: Network Rewiring using EXpression - Towards Context Specific Regulatory Networks
• Difference-of-Convex Elastic Net for Compressed Sensing
• On a general smoothly truncated regularization for variational piecewise constant image restoration: construction and convergent algorithms
• Convergence rate analysis of a sequential convex programming method with line search for a class of constrained difference-of-convex optimization problems
• The basins of attraction of the global minimizers of non-convex inverse\n problems with low-dimensional models in infinite dimension
• Robust Entity Alignment for Fuzzy Temporal Knowledge Graphs via Dynamic Vector Transformation and Optimal Transport
• Alternating Direction Method of Multipliers for A Class of Nonconvex and Nonsmooth Problems with Applications to Background/Foreground Extraction
• Projected Wirtinger Gradient Descent for Low-Rank Hankel Matrix Completion in Spectral Compressed Sensing
• C-SALT: Mining Class-Specific ALTerations in Boolean Matrix\n Factorization
• Non-smooth Variable Projection
• Group-sparse SVD Models and Their Applications in Biological Data
• Optimal Rank Selection for Nonnegative Matrix Factorization via ℓ_2,0-Norm Regularization
• Structured Nonconvex and Nonsmooth Optimization: Algorithms and Iteration Complexity Analysis
• Learning from the Descent Direction: Adaptive Gradient Descent under One-Sided Hölder Regularity
• Composite Difference-Max Programs for Modern Statistical Estimation Problems
• Coupled dictionary learning for unsupervised change detection between multi-sensor remote sensing images
• A Proximal Method for Composite Optimization with Smooth and Convex Components
• A preconditioned second-order convex splitting algorithm with extrapolation
• Convergence guarantees for a class of non-convex and non-smooth optimization problems
• Coordinate Descent Algorithms
• Convergent and efficient iteratively regularized contrast source inversion-type methods for inverse medium scattering problems
• The value function approach to convergence analysis in composite\n optimization
• The exact modulus of the generalized concave Kurdyka-Łojasiewicz property
• A nonmonotone extrapolated proximal gradient-subgradient algorithm beyond global Lipschitz gradient continuity
• Convergence of multi-block Bregman ADMM for nonconvex composite problems
• A novel multi-exposure-to-multi-mediator mediation model for imaging genetic study of brain disorders
• Worst-Case Load Shedding in Electric Power Networks
• iFCTN: Folding-Free Fully-Connected Tensor Network Decomposition for Tensor Completion
• DCA based Algorithm with Extrapolation for Nonconvex Nonsmooth\n Optimization
• Hyperspectral Super-Resolution with Inter-Image Variability via Degradation-based Low-Rank and Residual Fusion Method
• Two-stage toeplitz quasi-likelihood screening-refit for unknown-source-number DOA estimation with fully augmentable arrays
• Computing B-Stationary Points of Nonsmooth DC Programs
• Massive Access in Secure NOMA under Imperfect CSI: Security Guaranteed Sum-Rate Maximization with First-Order Algorithm
• Kurdyka-Lojasiewicz Property of Zero-Norm Composite Functions
• Time series forecasting from partial observations via Non-negative Matrix Factorization
• Minimizing smooth Kurdyka-Łojasiewicz functions via generalized descent methods: Convergence rate and complexity
• Non-Negative Stiefel Approximating Flow: Orthogonalish Matrix Optimization for Interpretable Embeddings
• Sparsity via Hyperpriors: A Theoretical and Algorithmic Study under Empirical Bayes Framework
• An efficient proximal algorithm for squared L1 over L2 regularized sparse recovery
• A Support-Set Algorithm for Optimization Problems with Nonnegative and Orthogonal Constraints
• Variable Smoothing Alternating Proximal Gradient Algorithm for Coupled Composite Optimization
• A flexible block-coordinate forward-backward algorithm for non-smooth and non-convex optimization
• Long term dynamics of the subgradient method for Lipschitz path\n differentiable functions
• A two-level distributed algorithm for nonconvex constrained optimization
• Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry
• On the convergence of higher-order orthogonality iteration
• FasTer: Fast Tensor Completion with Nonconvex Regularization
• Efficient Optimization Algorithms for Robust Principal Component Analysis and Its Variants
• Hyperspectral Unmixing With Spectral Variability Using a Perturbed Linear Mixing Model
• An iterative support shrinking algorithm for \ℓ_p-\ℓ_q\n minimization
• Comparison-Based Algorithms for One-Dimensional Stochastic Convex Optimization
• Blind inverse problems with isolated spikes
• PENDANTSS: PEnalized Norm-ratios Disentangling Additive Noise, Trend and Sparse Spikes
• Solving Optimization Problems over the Stiefel Manifold by Smooth Exact Penalty Function
• Stochastic Optimization for Non-convex Inf-Projection Problems
• Game-Theoretic Mixed H₂/H_∞ Control with Sparsity Constraint for Multi-agent Networked Control Systems
• Non-ergodic Complexity of Convex Proximal Inertial Gradient Descents
• Extended ADMM and BCD for Nonseparable Convex Minimization Models with Quadratic Coupling Terms: Convergence Analysis and Insights
• Convergence Analysis of Alternating Direction Method of Multipliers for a Family of Nonconvex Problems
• Stochastic Gradient Descent for Stochastic Doubly-Nonconvex Composite Optimization
• A stroll in the jungle of error bounds
• First-order majorization-minimization meets high-order majorant: Boosted inexact high-order forward-backward method
• Binno: A 1st-order method for Bi-level Nonconvex Nonsmooth Optimization for Matrix Factorizations
• Optimization of Bregman Variational Learning Dynamics
• Exact Sparse Orthogonal Dictionary Learning
• Solving nonconvex optimization problems via a second order dynamical system with unbounded damping
• Learning Multi-Index Models with Hyper-Kernel Ridge Regression
• A Proximal Linearization-based Decentralized Method for Nonconvex Problems with Nonlinear Constraints
• Approximate Bregman proximal gradient algorithm with variable metric Armijo--Wolfe line search
• Overlapping Domain Decomposition Methods for Ptychographic Imaging
• Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms
• Joint deconvolution and blind source separation on the sphere with an application to radio-astronomy
• Wavelet inpainting with the ℓ0 sparse regularization
• Nonlinear matrix recovery using optimization on the Grassmann manifold
• Conservative set valued fields, automatic differentiation, stochastic gradient method and deep learning
• On the Convergence of Learning-based Iterative Methods for Nonconvex Inverse Problems
• A two-level distributed algorithm for nonconvex constrained optimization
• Solving NMF with smoothness and sparsity constraints using PALM
• A Scale Invariant Approach for Sparse Signal Recovery
• Joint Cooperative and Non-Cooperative Localization in WSNs with Distributed Scaled Proximal ADMM Algorithms
• On the Convergence of Muon and Beyond
• Joint Learning of Panel VAR models with Low Rank and Sparse Structure
• Linear convergence of inexact descent method and inexact proximal gradient algorithms for lower-order regularization problems
• A sparse semismooth Newton based proximal majorization-minimization algorithm for nonconvex square-root-loss regression problems
• Simple linesearch-free first-order methods for nonconvex optimization
• Low Rank Approximation of Tensors via Sparse Optimization
• On Accelerating the Regularized Alternating Least Square Algorithm for Tensors
• Distributed Proximal Gradient Algorithm for Partially Asynchronous\n Computer Clusters
• Convergence of Bregman alternating direction method with multipliers for nonconvex composite problems
• Constraint hypergraph partitioning problems via recursive bipartition algorithm based on improved Dai–Kou conjugate gradient algorithm
• A preconditioned third-order implicit-explicit algorithm with a difference of varying convex functions and extrapolation
• A new nonlocal low-rank regularization method with applications to magnetic resonance image denoising
• An Inexact Riemannian Proximal Gradient Method
• A Globalized Semismooth Newton Method for Prox-regular Optimization Problems
• A trust region-type normal map-based semismooth Newton method for nonsmooth nonconvex composite optimization
• Accelerated Block Coordinate Proximal Gradients with Applications in\n High Dimensional Statistics
• Solving Imaging Inverse Problems Using Plug-and-Play Denoisers: Regularization and Optimization Perspectives
• Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases
• Controllability maximization of large-scale systems using projected gradient method
• Deeply-Sparse Signal rePresentations (DS²P)
• Iteratively reweighted ℓ ₁ ℓ 1 algorithms with extrapolation
• Accelerated Proximal Dogleg Majorization for Sparse Regularized Quadratic Optimization Problem
• A Semismooth Newton based Augmented Lagrangian Method for Nonsmooth Optimization on Matrix Manifolds
• Supervised Stochastic Gradient Algorithms for Multi-Trial Source Separation
• Efficient Rank Minimization via Solving Non-convexPenalties by Iterative Shrinkage-Thresholding Algorithm
• A New Inexact Manifold Proximal Linear Algorithm with Adaptive Stopping Criteria
• The Geometry of Constrained Optimization: Constrained Gradient Flows via Reparameterization: A-Stable Implicit Schemes, KKT from Stationarity, and Geometry-Respecting Algorithms
• A smoothed proximal trust-region algorithm for nonconvex optimization problems with L^p-regularization, p∈ (0,1)
• An inexact variable metric proximal linearization method for composite optimization over embedded submanifolds
• Block Distributed Majorize-Minimize Memory Gradient Algorithm and its\n application to 3D image restoration
• A Convergent Generalized Krylov Subspace Method for Compressed Sensing MRI Reconstruction with Gradient-Driven Denoisers
• Provable Bregman-divergence based Methods for Nonconvex and Non-Lipschitz Problems
• Sparsity Constrained Minimization via Mathematical Programming with Equilibrium Constraints
• LRTuckerRep: Low-rank Tucker Representation Model for Multi-dimensional Data Completion
• ConFuse: Convolutional Transform Learning Fusion Framework For\n Multi-Channel Data Analysis
• The Kurdyka-Łojasiewicz inequality as regularity condition
• LAMA-Net: A Convergent Network Architecture for Dual-Domain Reconstruction
• Nonconvex Optimization Framework for Group-Sparse Feedback Linear-Quadratic Optimal Control: Non-Penalty Approach
• An inexact alternating projection method with application to matrix completion
• Learning Latent Features with Pairwise Penalties in Low-Rank Matrix Completion
• A Preconditioned Difference of Convex Algorithm for Truncated Quadratic Regularization with Application to Imaging
• Speech Enhancement with Dual-path Multi-Channel Linear Prediction Filter and Multi-norm Beamforming
• General Proximal Quasi-Newton Methods based on model functions for nonsmooth nonconvex problems
• Effective two-stage image segmentation: a new non-Lipschitz decomposition approach with convergent algorithm
• Low Tensor Train- and Low Multilinear Rank Approximations for De-speckling and Compression of 3D Optical Coherence Tomography Images