Sparse recovery via differential inclusions

DOI10.1016/j.acha.2016.01.002zbMath1360.94090arXiv1406.7728OpenAlexW289002709MaRDI QIDQ739470

Yuan Yao, Wotao Yin, Jiechao Xiong, Feng Ruan, Stanley J. Osher

Publication date: 18 August 2016

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1406.7728

zbMATH Keywords

differential inclusionstatistical consistencyearly stopping regularizationinverse scale space (ISS)linearized Bregman

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07) Applications of statistics (62P99) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Related Items (8)

Adaptive multi-penalty regularization based on a generalized Lasso path ⋮ Bias reduction in variational regularization ⋮ Boosting with structural sparsity: a differential inclusion approach ⋮ Evaluating visual properties via robust HodgeRank ⋮ On Lasso refitting strategies ⋮ Choose Your Path Wisely: Gradient Descent in a Bregman Distance Framework ⋮ CLEAR: Covariant LEAst-Square Refitting with Applications to Image Restoration ⋮ Implicit regularization with strongly convex bias: Stability and acceleration

Uses Software

• PDCO

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Greedy function approximation: A gradient boosting machine.
• The Adaptive Lasso and Its Oracle Properties
• Error estimation for Bregman iterations and inverse scale space methods in image restoration
• Least angle regression. (With discussion)
• Nonlinear inverse scale space methods
• Multiplier and gradient methods
• On early stopping in gradient descent learning
• The stability of solutions of linear differential equations
• Augmented $\ell_1$ and Nuclear-Norm Models with a Globally Linearly Convergent Algorithm
• Analysis and Generalizations of the Linearized Bregman Method
• A Singular Value Thresholding Algorithm for Matrix Completion
• Adapting to Unknown Smoothness via Wavelet Shrinkage
• A generalization of a lemma of bellman and its application to uniqueness problems of differential equations
• Fixed-Point Continuation for $\ell_1$-Minimization: Methodology and Convergence
• Inverse Total Variation Flow
• Greed is Good: Algorithmic Results for Sparse Approximation
• Atomic Decomposition by Basis Pursuit
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Boosting With theL₂Loss
• Nonlinear wavelet image processing: variational problems, compression, and noise removal through wavelet shrinkage
• Uncertainty principles and ideal atomic decomposition
• An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
• De-noising by soft-thresholding
• An adaptive inverse scale space method for compressed sensing
• Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using $\ell _{1}$-Constrained Quadratic Programming (Lasso)
• On Recovery of Sparse Signals Via $\ell _{1}$ Minimization
• Minimax Rates of Estimation for High-Dimensional Linear Regression Over $\ell_q$-Balls
• Orthogonal Matching Pursuit for Sparse Signal Recovery With Noise
• Stable Recovery of Sparse Signals and an Oracle Inequality
• Regularization and Variable Selection Via the Elastic Net
• On the Non-Negative Garrotte Estimator
• Bregman Iterative Algorithms for $\ell_1$-Minimization with Applications to Compressed Sensing
• Variational, Geometric, and Level Set Methods in Computer Vision
• An Iterative Regularization Method for Total Variation-Based Image Restoration
• Compressed sensing

This page was built for publication: Sparse recovery via differential inclusions