Lasso and Elastic-Net Regularized Generalized Linear Models.

Lasso and Elastic-Net Regularized Generalized Linear Models

We provide extremely efficient procedures for fitting the entire lasso or elastic-net regularization path for linear regression (gaussian), multi-task gaussian, logistic and multinomial regression models (grouped or not), Poisson regression and the Cox model. The algorithm uses cyclical coordinate descent in a path-wise fashion. Details may be found in Friedman, Hastie, and Tibshirani (2010), Simon et al. (2011), Tibshirani et al. (2012), Simon, Friedman, and Hastie (2013).

Version 3.0 is a major release with several new features, including:

• Relaxed fitting to allow models in the path to be refit without regularization. CV will select from these, or from specified mixtures of the relaxed fit and the regular fit;
• Progress bar to monitor computation;
• Assessment functions for displaying performance of models on test data. These include all the measures available via cv.glmnet, as well as confusion matrices and ROC plots for classification models;
• print methods for CV output;
• Functions for building the x input matrix for glmnet that allow for one-hot-encoding of factor variables, appropriate treatment of missing values, and an option to create a sparse matrix if appropriate.
• A function for fitting unpenalized a single version of any of the GLMs of glmnet.

Version 4.0 is a major release that allows for any GLM family, besides the built-in families.

Version 4.1 is a major release that expands the scope for survival modeling, allowing for (start, stop) data, strata, and sparse X inputs. It also provides a much-requested method for survival:survfit.

References