skip to main content
Resource type Show Results with: Show Results with: Index

Distributed Coordinate Descent for L1-regularized Logistic Regression

Trofimov, Ilya ; Genkin, Alexander

Analysis of Images, Social Networks and Texts. Fourth International Conference, AIST 2015, Yekaterinburg, Russia, April 9-11, 2015, Revised Selected Papers. Communications in Computer and Information Science, Vol. 542, 243-254, Springer [Peer Reviewed Journal]

Link to full text

Citations Cited by
  • Title:
    Distributed Coordinate Descent for L1-regularized Logistic Regression
  • Author/Creator: Trofimov, Ilya ; Genkin, Alexander
  • Subjects: Statistics - Machine Learning ; Computer Science - Learning
  • Is Part Of: Analysis of Images, Social Networks and Texts. Fourth International Conference, AIST 2015, Yekaterinburg, Russia, April 9-11, 2015, Revised Selected Papers. Communications in Computer and Information Science, Vol. 542, 243-254, Springer
  • Description: 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.
  • Identifier: Arxiv ID: 1411.6520