iterreg

Fast iterative regularization approach for non strongly convex regularizers, e.g. sparsity (L1) or low rank (nuclear norm).

Documentation

Please visit https://LCSL.github.io/iterreg/ for the latest version of the documentation.

Install and work with the development version

From a console or terminal clone the repository and install iterreg:

git clone https://github.com/LCSL/iterreg.git
cd iterreg/
pip install -e .

To build the documentation you will need to run:

cd doc/
pip install doc_requirements.txt
make html

Demos & Examples

In the example section of the documentation, you will find scripts to reproduce the figures of the paper.

Dependencies

All dependencies are in the ./requirements.txt file. They are installed automatically when pip install -e . is run.

Cite

If you use this code, please cite:

@inproceedings{iterreg,
  title = {Iterative regularization with convex regularizers},
  author = {Molinari, Cesare and Massias, Mathurin and Rosasco, Lorenzo and Villa, Silvia},
  booktitle = AISTATS,
  year = 2021,
}

ArXiv links:

• https://arxiv.org/abs/2006.09859