Fast projections onto mixed-norm balls with applications

DOI10.1007/s10618-012-0277-7zbMath1260.90162arXiv1204.1437MaRDI QIDQ1944995

Suvrit Sra

Publication date: 28 March 2013

Published in: Data Mining and Knowledge Discovery (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1204.1437

zbMATH Keywords

matrix norms; group sparsity; stochastic gradient; mixed-norm; multitask learning; fast projection

Mathematics Subject Classification ID

62J07: Ridge regression; shrinkage estimators (Lasso)

90C52: Methods of reduced gradient type

Uses Software

• UNLocBoX
• SLEP

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Sparse regression using mixed norms
• Input selection and shrinkage in multiresponse linear regression
• Algorithms for simultaneous sparse approximation. II: Convex relaxation
• The composite absolute penalties family for grouped and hierarchical variable selection
• A finite algorithm for finding the projection of a point onto the canonical simplex of \({\mathbb R}^ n\)
• Projected Barzilai-Borwein methods for large-scale box-constrained quadratic programming
• On linear-time algorithms for the continuous quadratic Knapsack problem
• Proximal Splitting Methods in Signal Processing
• Optimization with Sparsity-Inducing Penalties
• A Singular Value Thresholding Algorithm for Matrix Completion
• The Gradient Projection Method for Nonlinear Programming. Part I. Linear Constraints
• Two-Point Step Size Gradient Methods
• A generalized proximal point algorithm for certain non-convex minimization problems
• Inexact spectral projected gradient methods on convex sets
• Nonmonotone Spectral Projected Gradient Methods on Convex Sets
• De-noising by soft-thresholding
• Model Selection and Estimation in Regression with Grouped Variables