celer 0.4

Fast algorithm with dual extrapolation for the Lasso

celer

Fast algorithm to solve the Lasso with dual extrapolation

Documentation

Please visit https://mathurinm.github.io/celer/ for the latest version of the documentation.

Install the released version

Assuming you have a working Python environment, e.g. with Anaconda you can install celer with pip.

From a console or terminal install celer with pip:

pip install -U celer

To setup a fully functional environment we recommend you download this conda environment and install it with:

conda env create --file environment.yml

Install the development version

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

git clone https://github.com/mathurinm/celer.git
cd celer/
conda env create --file environment.yml
source activate celer-env
pip install --no-deps -e .

Demos & Examples

You find on the documentation examples on the Leukemia dataset (comparison with scikit-learn) and on the Finance/log1p dataset (more significant, but it takes times to download the data, preprocess it, and compute the path).

Dependencies

All dependencies are in ./environment.yml

Cite

If you use this code, please cite:

@InProceedings{pmlr-v80-massias18a,
  title =    {Celer: a Fast Solver for the Lasso with Dual Extrapolation},
  author =   {Massias, Mathurin and Gramfort, Alexandre and Salmon, Joseph},
  booktitle =        {Proceedings of the 35th International Conference on Machine Learning},
  pages =    {3321--3330},
  year =     {2018},
  volume =   {80},
}

ArXiv link: https://arxiv.org/abs/1802.07481