Home Software PASPAL
Home Software PASPAL

PASPAL (Proximal Algorithms for SPArse Learning) is a set of MATLAB toolboxes that implement different regularization approaches to sparse learning (lasso, elastic net, group lasso, and group lasso with overlap). Click here to visit the PASPAL page and download the code

The optimization procedure for solving the various regularization problems is based on proximal methods and is described in [1,2].


  1. S. Mosci, L. Rosasco, M. Santoro, A. Verri and S. Villa; Solving Structured Sparsity Regularization with Proximal Methods; in J.L. Balcazar, F. Bonchi, A. Gionis and M. Sebag (Eds.), Machine Learning and Knowledge Discovery in Databases, European Conference, ECML PKDD 2010, Barcelona, Spain, September 20-24, 2010, Proceedings, Part II pp 418.
  2. S. Mosci, S. Villa, A. Verri, L. Rosasco; A primal-dual algorithm for group sparse regularization with overlapping groups; To be presented at NIPS 2010.