Activity Identification and Local Linear Convergence of Forward--Backward-type Methods
From MaRDI portal
Publication:2968179
DOI10.1137/16M106340XzbMath1357.49064arXiv1503.03703OpenAlexW2964094444MaRDI QIDQ2968179
Jalal Fadili, Gabriel Peyré, Jingwei Liang
Publication date: 10 March 2017
Published in: SIAM Journal on Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1503.03703
Numerical mathematical programming methods (65K05) Convex programming (90C25) Numerical optimization and variational techniques (65K10) Sensitivity, stability, parametric optimization (90C31) Nonsmooth analysis (49J52)
Related Items
A Trust-region Method for Nonsmooth Nonconvex Optimization, Nonsmoothness in machine learning: specific structure, proximal identification, and applications, Sensitivity Analysis for Mirror-Stratifiable Convex Functions, Improving “Fast Iterative Shrinkage-Thresholding Algorithm”: Faster, Smarter, and Greedier, Local convergence properties of Douglas-Rachford and alternating direction method of multipliers, Active-Set Identification with Complexity Guarantees of an Almost Cyclic 2-Coordinate Descent Method with Armijo Line Search, An active set Newton-CG method for \(\ell_1\) optimization, From error bounds to the complexity of first-order descent methods for convex functions, On the strong convergence of forward-backward splitting in reconstructing jointly sparse signals, Quadratic growth conditions and uniqueness of optimal solution to Lasso, ``FISTA in Banach spaces with adaptive discretisations, Newton acceleration on manifolds identified by proximal gradient methods, Fast gradient method for low-rank matrix estimation, Thresholding gradient methods in Hilbert spaces: support identification and linear convergence, Screening Rules and its Complexity for Active Set Identification, Nonmonotone globalization for Anderson acceleration via adaptive regularization, Convergence rates of the heavy-ball method under the Łojasiewicz property, Convergence of the forward-backward algorithm: beyond the worst-case with the help of geometry, A forward-backward algorithm with different inertial terms for structured non-convex minimization problems, Accelerating inexact successive quadratic approximation for regularized optimization through manifold identification, Local linear convergence of proximal coordinate descent algorithm, Inertial forward-backward algorithms with perturbations: application to Tikhonov regularization, An explicit algorithm for solving monotone variational inequalities, Unnamed Item, Local linear convergence analysis of Primal–Dual splitting methods, Local and global convergence of a general inertial proximal splitting scheme for minimizing composite functions, Convergence rates of an inertial gradient descent algorithm under growth and flatness conditions, On the interplay between acceleration and identification for the proximal gradient algorithm, On the linear convergence of forward-backward splitting method. I: Convergence analysis, Functional penalised basis pursuit on spheres, The sliding Frank–Wolfe algorithm and its application to super-resolution microscopy, A projected extrapolated gradient method with larger step size for monotone variational inequalities, Faster subgradient methods for functions with Hölderian growth, Structure and Optimisation in Computational Harmonic Analysis: On Key Aspects in Sparse Regularisation, An active set Barzilar-Borwein algorithm for \(l_0\) regularized optimization, ``Active-set complexity of proximal gradient: how long does it take to find the sparsity pattern?, Convergence rates of forward-Douglas-Rachford splitting method, A fast conjugate gradient algorithm with active set prediction for ℓ1 optimization, Active‐Set Newton Methods and Partial Smoothness, Proximal Gradient Methods with Adaptive Subspace Sampling
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- Fast convex optimization via inertial dynamics with Hessian driven damping
- Gradient methods for minimizing composite functions
- ParNes: A rapidly convergent algorithm for accurate recovery of sparse and approximately sparse signals
- On the convergence of the iterates of the ``fast iterative shrinkage/thresholding algorithm
- Linear convergence of iterative soft-thresholding
- Fast global convergence of gradient methods for high-dimensional statistical recovery
- An inertial forward-backward algorithm for monotone inclusions
- A coordinate gradient descent method for nonsmooth separable minimization
- Introductory lectures on convex optimization. A basic course.
- Convergence of a splitting inertial proximal method for monotone operators
- \(\varepsilon\)-enlargements of maximal monotone operators in Banach spaces
- Adaptive restart for accelerated gradient schemes
- Fast convergence of inertial dynamics and algorithms with asymptotic vanishing viscosity
- Set-valued mappings and enlargement of monotone operators.
- Newton methods for nonsmooth convex minimization: connections among \(\mathcal U\)-Lagrangian, Riemannian Newton and SQP methods
- The Rate of Convergence of Nesterov's Accelerated Forward-Backward Method is Actually Faster Than $1/k^2$
- Identifying Active Manifolds in Regularization Problems
- Orthogonal Invariance and Identifiability
- Local Linear Convergence of ISTA and FISTA on the LASSO Problem
- Identifiable Surfaces in Constrained Optimization
- Fixed-Point Continuation for $\ell_1$-Minimization: Methodology and Convergence
- Geometrical interpretation of the predictor-corrector type algorithms in structured optimization problems
- Stability of Over-Relaxations for the Forward-Backward Algorithm, Application to FISTA
- Splitting Algorithms for the Sum of Two Nonlinear Operators
- Optimization Techniques on Riemannian Manifolds
- Variational Analysis
- Tilt Stability of a Local Minimum
- On the Minimizing Property of a Second Order Dissipative System in Hilbert Spaces
- Model Consistency of Partly Smooth Regularizers
- Model selection with low complexity priors
- The 𝒰-Lagrangian of a convex function
- Active Sets, Nonsmoothness, and Sensitivity
- A Dynamical Approach to an Inertial Forward-Backward Algorithm for Convex Minimization
- Fast Alternating Direction Optimization Methods
- Partial Smoothness, Tilt Stability, and Generalized Hessians
- Fast Gradient-Based Algorithms for Constrained Total Variation Image Denoising and Deblurring Problems
- An Extrinsic Look at the Riemannian Hessian
- The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
- Variable metric forward–backward splitting with applications to monotone inclusions in duality
- Some methods of speeding up the convergence of iteration methods
- Weak convergence of the sequence of successive approximations for nonexpansive mappings
- Convex analysis and monotone operator theory in Hilbert spaces
- An inertial proximal method for maximal monotone operators via discretization of a nonlinear oscillator with damping
