Learning Theory of Randomized Sparse Kaczmarz Method

DOI10.1137/17M1136225zbMath1437.94020OpenAlexW2787899424MaRDI QIDQ4686926

Ding-Xuan Zhou, Yunwen Lei

Publication date: 10 October 2018

Published in: SIAM Journal on Imaging Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/17m1136225

zbMATH Keywords

learning theoryonline learningBregman distancelinearized Bregman iterationrandomized sparse Kaczmarz algorithm

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Iterative numerical methods for linear systems (65F10)

Related Items (3)

A semi-randomized Kaczmarz method with simple random sampling for large-scale linear systems ⋮ On convergence rates of Kaczmarz-type methods with different selection rules of working rows ⋮ Analysis of singular value thresholding algorithm for matrix completion

Uses Software

• AIR tools

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Consistency analysis of an empirical minimum error entropy algorithm
• Concentration estimates for learning with \(\ell ^{1}\)-regularizer and data dependent hypothesis spaces
• A unified primal-dual algorithm framework based on Bregman iteration
• A randomized Kaczmarz algorithm with exponential convergence
• Strong conical hull intersection property, bounded linear regularity, Jameson's property \((G)\), and error bounds in convex optimization
• AIR tools -- a MATLAB package of algebraic iterative reconstruction methods
• Randomized Extended Kaczmarz for Solving Least Squares
• The Linearized Bregman Method via Split Feasibility Problems: Analysis and Generalizations
• Online Learning as Stochastic Approximation of Regularization Paths: Optimality and Almost-Sure Convergence
• Analysis and Generalizations of the Linearized Bregman Method
• Linearized Bregman iterations for compressed sensing
• Convergence of the linearized Bregman iteration for ℓ₁-norm minimization
• The Split Bregman Method for L1-Regularized Problems
• Learning Theory
• Online Regularized Classification Algorithms
• ONLINE LEARNING WITH MARKOV SAMPLING
• Bregman Monotone Optimization Algorithms
• On Projection Algorithms for Solving Convex Feasibility Problems
• Regularization schemes for minimum error entropy principle
• Thresholded spectral algorithms for sparse approximations
• Analysis of Online Composite Mirror Descent Algorithm
• Bregman Iterative Algorithms for $\ell_1$-Minimization with Applications to Compressed Sensing

This page was built for publication: Learning Theory of Randomized Sparse Kaczmarz Method