Extension of LIBLINEAR for data which cannot fit in memory
Extension of LIBLINEAR for data which cannot fit in memory. Currently it supports L2-regularized L1- and L2- loss linear SVM for binary classification problem and Cramer and Singer formulation for multi-class classification problem.
LIBLINEAR is a linear classifier for data with millions of instances and features. It supports
* L2-regularized classifiers
* L2-loss linear SVM, L1-loss linear SVM, and logistic regression (LR)
* L1-regularized classifiers (after version 1.4)
* L2-loss linear SVM and logistic regression (LR)