/Group-FOS

This repository contains the software for the group-FOS estimator.

Primary LanguageMATLAB

Group-FOS

This repository provides the implementations of the methods described in [Balancing Statistical and Computational Precision and Applications to Penalized Linear Regression with Group Sparsity].

Requirements

You need to install SPAMS toolbox.

Usage

Files NewFOS.m and GroupFOS.m contain functions FOS and Group-FOS.
Files FOS_log_reg.m contain functions for log-FOS.

Simulations

We provide an example code in script_simulation_GroupFOS.m for linear regression . We provide an example code in script_simulation_logFOS.m for logistic regression .

Repository Authors

  • Mahsa Taheri, Ph.D. student in Mathematical Statistics, Ruhr-University Bochum

  • Nehemy Lim, Professor in Department of Statistics, University of Connecticut

  • Johannes Lederer, Professor in Mathematical Statistics, Ruhr-University Bochum

Other files

simulate_linear_regression.m generates data and simulate_linear_regression_group.m generates structured data. simulate_logistic_regression.m generates data for logistic regression example.

Supported Languages and platforms

All of the codes in this repository are written in MATLAB and supports all plarforms which are supported by MATLAB itself.

Licensing

The HDIM package is licensed under the MIT license. To view the MIT license please consult LICENSE.txt.

References

[Balancing Statistical and Computational Precision and Applications to Penalized Linear Regression with Group Sparsity]