A Library for Online Learning Algorithms

Revision History:

  • 12/12/2013
    Version 0.3.0 main changes:

        • Add a template and guide for adding new algorithms;
        • Improve parameter settings and documentation ;
        • Improve documentation on data formats and key functions;

        • Amend the "OGD" function to use different loss types;
        • Make some names consistent and fixed some minor bugs


  • 23/09/2013
    Version 0.2.3 main changes:

        • Make the library fully compatible with Octave;
        • Include C/C++ function rand_c for random generator;
        • Include arg_check to check argument validation;
        • Fixed some other bugs.


  • 27/07/2013
    Version 0.2.0 main changes:
    • • Support online multicclass classification;
      • C/C++ implementation for core functions;
      • 16 algorithms and variants for binary classification;
      • 13 algorithms and variants for multiclass classification.


  • 27/12/2012
    Version 0.1.0: The MATLAB beta version is now availabe! It supports binary classification.

  • 6/7/2012
    The MATLAB alpha version is availabe for testing upon email request.


TODO list:

  • Incoporate the AUC maximization algorithms
  • Incorporate the cost-sensitive online learning algorithms
  • Incoporate the kernel-based online learning algorithms