## Abstract

We develop an R package fastclime for solving a family of regularized linear programming (LP) problems. Our package effciently implements the parametric simplex algorithm, which provides a scalable and sophisticated tool for solving large-scale linear programs. As an illustrative example, one use of our LP solver is to implement an important sparse precision matrix estimation method called CLIME (Constrained L1 Minimization Estimator). Compared with existing packages for this problem such as clime and flare, our package has three advantages: (1) it effciently calculates the full piecewise-linear regularization path; (2) it provides an accurate dual certificate as stopping criterion; (3) it is completely coded in C and is highly portable. This package is designed to be useful to statisticians and machine learning researchers for solving a wide range of problems.

Original language | English (US) |
---|---|

Pages (from-to) | 489-493 |

Number of pages | 5 |

Journal | Journal of Machine Learning Research |

Volume | 15 |

State | Published - Jan 1 2014 |

## Keywords

- High dimensional data
- Linear programming
- Parametric simplex method
- Sparse precision matrix
- Undirected graphical model

## ASJC Scopus subject areas

- Control and Systems Engineering
- Software
- Statistics and Probability
- Artificial Intelligence