Distributed Coordinate Descent for L1-regularized Logistic Regression

11/24/2014

∙

by   Ilya Trofimov, et al.

∙

0

∙

share

Solving logistic regression with L1-regularization in distributed settings is an important problem. This problem arises when training dataset is very large and cannot fit the memory of a single machine. We present d-GLMNET, a new algorithm solving logistic regression with L1-regularization in the distributed settings. We empirically show that it is superior over distributed online learning via truncated gradient.