links | publications | code
ron

Ron Begleiter

I have graduated. My Ph.D. thesis advisors were Prof. Nir Ailon and Prof. Ran El-Yaniv.
My main research interests cover machine learning, and sequence prediction.

publications

  • N. Ailon, R. Begleiter and E. Ezra.
    Active Learning Using Smooth Relative Regret Approximations with Applications.
    Journal of Machine Learning Research, 15:885--920, 2014 [link]
  • R. Begleiter, Y. Elovici, Y. Hollander, O. Mendelson, L. Rokach, and R. Saltzman.
    A Fast and Scalable Method for Threat Detection in Large-scale DNS Logs.
    IEEE BigData 2013 (industry and government program) [link]
  • N. Ailon, R. Begleiter, E. Ezra.
    Active Learning Using Smooth Relative Regret Approximations with Applications.
    COLT 2012 [pdf] (Best Student Paper Award)
  • R. Begleiter, R. El-Yaniv and D. Pechyony.
    Repairing Self-Confident Active-Transductive Learners Using Systematic Exploration.
    Pattern Recognition Letters, 29.9:1245--1251, 2008 [link]
  • R. Begleiter and R. El-Yaniv.
    Superior Guarantees for Sequential Prediction and Lossless Compression via Alphabet Decomposition.
    Journal of Machine Learning Research, 7:379--411, 2006 [pdf]
  • R. Begleiter, R. El-Yaniv and G. Yona.
    On Prediction Using Variable Order Markov Models.
    Journal of Artificial Intelligence Research, 22:385--421, 2004 [pdf]

Code

  • Online learning distributions /Ruby 1.9.x/gem/Open source/ [gem-link] [code-link]
  • Generic k-fold cross-validation /Matlab/Parallel computation/Open source/ [link]
  • Variable order markov models (VMMs) /Java/Matlab/Sequence Prediction/Open source/ [link]
  • Active learning /Java/Matlab/Open source/ [link]