zeroSR1

Version 1.0.0.0 (196 KB) by Stephen Becker

Very fast code for solving lasso and non-negative least-squares problems

https://github.com/stephenbeckr/zeroSR1

0.0

(0)

546 Downloads

Updated 27 Dec 2024

View License on GitHub

Proximal gradient algorithm for convex optimization, using a diagonal +/- rank-1 norm. Uses special tricks to allow the use of a quasi-Newton methods.

Cite As

Stephen Becker (2026). zeroSR1 (https://github.com/stephenbeckr/zeroSR1), GitHub. Retrieved January 9, 2026.

MATLAB Release Compatibility

Created with R2011a

Compatible with any release

Platform Compatibility

Windows macOS Linux

Tags Add Tags

Acknowledgements

Inspired by: NNLS and constrained regression, predictor-corrector algorithm, nnls, active set algorithm, newton's algorithm for nnls, MTRON, LARS algorithm, LBFGSB (L-BFGS-B) mex wrapper, mex interface for bound constrained optimization via ASA, nnls - Non negative least squares, Simple MATLAB example code and generic function to perform LASSO

Inspired: mex interface for bound constrained optimization via ASA

setup_zeroSR1

algorithms

zeroSR1

paperExperiments/Lasso

proxes

smoothFunctions

tests

utilities

Versions that use the GitHub default branch cannot be downloaded

Version	Published	Release Notes
1.0.0.0	27 Dec 2024

To view or report issues in this GitHub add-on, visit the GitHub Repository.