Thresholding gradient methods in Hilbert spaces: support identification and linear convergence

DOI10.1051/cocv/2019011MaRDI QIDQ5109200

Silvia Villa, Lorenzo Rosasco, Guillaume Garrigos

Publication date: 11 May 2020

Published in: ESAIM: Control, Optimisation and Calculus of Variations (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1712.00357

zbMATH Keywords

convergence rates; conditioning; forward-backward method; support identification

Mathematics Subject Classification ID

90C25: Convex programming

90C46: Optimality conditions and duality in mathematical programming

65J10: Numerical solutions to equations with linear operators

65J15: Numerical solutions to equations with nonlinear operators

65J20: Numerical solutions of ill-posed problems in abstract spaces; regularization

65J22: Numerical solution to inverse problems in abstract spaces

65K15: Numerical methods for variational inequalities and related problems

Related Items

Convergence rates of gradient methods for convex optimization in the space of measures, Nonsmoothness in machine learning: specific structure, proximal identification, and applications, On the linear convergence of forward-backward splitting method. I: Convergence analysis, On the strong convergence of forward-backward splitting in reconstructing jointly sparse signals, Quadratic growth conditions and uniqueness of optimal solution to Lasso, Convergence of the forward-backward algorithm: beyond the worst-case with the help of geometry

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A necessary and sufficient condition for exact sparse recovery by \(\ell_1\) minimization
• Linear convergence of iterative soft-thresholding
• On the convergence of the proximal algorithm for nonsmooth functions involving analytic features
• Elastic-net regularization in learning theory
• Partially finite convex programming. I: Quasi relative interiors and duality theory
• A family of functional inequalities: Łojasiewicz inequalities and displacement convex functions
• From error bounds to the complexity of first-order descent methods for convex functions
• Maximal solutions of sparse analysis regularization
• Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
• Global error bounds for piecewise convex polynomials
• ``Active-set complexity of proximal gradient: how long does it take to find the sparsity pattern?
• Splitting methods with variable metric for Kurdyka-Łojasiewicz functions and general convergence rates
• Linear convergence of first order methods for non-strongly convex optimization
• Convergence of the forward-backward algorithm: beyond the worst-case with the help of geometry
• Nonparametric sparsity and regularization
• Convex Optimization in Normed Spaces
• Activity Identification and Local Linear Convergence of Forward--Backward-type Methods
• Evolution equations for maximal monotone operators: asymptotic analysis in continuous and discrete time
• Fixed-Point Continuation for $\ell_1$-Minimization: Methodology and Convergence
• Proximal Thresholding Algorithm for Minimization over Orthonormal Bases
• Sensitivity Analysis for Mirror-Stratifiable Convex Functions
• Regularized learning schemes in feature Banach spaces
• An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
• Error Bounds, Quadratic Growth, and Linear Convergence of Proximal Methods
• Regularization and Variable Selection Via the Elastic Net
• Convergence Rate Analysis of Several Splitting Schemes
• Sparse spikes super-resolution on thin grids II: the continuous basis pursuit
• Convex Analysis
• Convex analysis and monotone operator theory in Hilbert spaces