Tony Jebara


Mail Code 0401

Tel(212) 939-7079
Fax (212) 666-0140

Tony Jebara works on machine learning and statistical inference. Learning involves fitting models to large-scale data by optimally estimating parameters and structure. Inference involves using these models to predict labels of interest or finding the most likely and marginal configurations of any hidden variables of interest. The models Jebara focuses on are probabilistic graphical models: large networks which describe the conditional independencies between variables in a system.

Research Interests

Machine learning, statistics, optimization, recommendation engines, social networks, graph algorithms.

Jebara has created algorithms that apply graphical models to social networks, recommendation engines, power networks, financial networks, news/social media, mobile communication networks, co-location networks, brain neuron networks, program execution graphs, and more. Real-world applications include modeling social network data to enable friend recommendation, modeling mobile phone data-sets (such as call-detail records) to find users with similar behavior, and personalizing recommendation systems to suggest items of interest to users.

Jebara received a Bachelor’s degree in honors Electrical Engineering from McGill University in 1996, an MS degree in Media Arts & Sciences from MIT in 1998 and a PhD degree in Media Arts & Sciences from MIT in 2002. In 2004, Jebara was the recipient of the Career award from the National Science Foundation. His work was recognized with a best paper award at the 26th International Conference on Machine Learning, a best student paper award at the 20th International Conference on Machine Learning as well as an outstanding contribution award from the Pattern Recognition Society in 2001. Jebara was the Program Chair of the 2014 ICML conference and is the General Chair of the 2017 ICML conference. Esquire magazine named him one of their Best and Brightest of 2008. 


  • Associate professor of computer science, Columbia University, 2008–
  • Assistant professor of computer science, Columbia University, 2002–2007


  • International Machine Learning Society (IMLS)
  • Institute of Electrical and Electronics Engineers (IEEE)
  • Association for the Advancement of Artificial Intelligence (AAAI)
  • Association for Computing Machinery (ACM)


  • Neural and Cognitive Computation Chair Professor at Tsinghua University, 2013-2015
  • IBM Faculty Award, 2013
  • Yahoo Faculty Award, 2011
  • Google Faculty Award, 2009
  • Best Paper Award at the 26th International Conference on Machine Learning, 2009
  • IEEE ICTAI Award for Contributions to Artificial Intelligence, 2009
  • National Science Foundation Career Award, 2004
  • Best Student Paper Award at the 20th International Conference on Machine Learning, 2003
  • Honorable Mention Winner of the 27th Annual Pattern Recognition Society Award, 2001


  • Deciphering the cortex: circuit inference from large-scale brain activity data, DARPA BAA-14-59-SIMPLEX-FP-024 (Paninski, Jebara, Blei, Yuste). Total grant $2,103,864, 2015-2018.
  • Approximate Learning and Inference in Graphical Models, NSF III-1526914 (PI: Jebara), $164,089, 2015-2018
  • EAGER: New Optimization Methods for Machine Learning (PI: Jebara) $100,000, 2014-2018.


  • D. Tang and T. Jebara. Initialization and coordinate optimization for multi-way matching.  Artificial Intelligence and Statistics (AISTATs), April 2017.
  • G. Gidel, S. Lacoste-Julien and T. Jebara. Frank-Wolfe algorithms for saddle point problems. Artificial Intelligence and Statistics (AISTATs), April 2017.
  • A. Choromanska, K. Choromanski, M. Bojarski, T. Jebara, S. Kumar, Y. LeCun. Binary embeddings with structured hashed projections. International Conference on Machine Learning (ICML), June 2016.
  • K. Tang, N. Ruozzi, D. Belanger, and T. Jebara. Bethe learning of graphical models via MAP decoding. International Conference on Artificial Intelligence and Statistics (AISTATs), May 2016.
  • S.M. Bellovin, R.M. Hutchins, T. Jebara and S. Zimmeck, When Enough is Enough: Location Tracking, Mosaic Theory and Machine Learning, 8 New York University Journal of Law & Liberty 556 (2014).
  • J. Wang, T. Jebara and S.-F. Chang. Semi-Supervised Learning Using Greedy Max-Cut. Journal of Machine Learning Research, Volume 14, pages 771-800, 2013.
  • T. Jebara. Multitask Sparsity via Maximum Entropy Discrimination. Journal of Machine Learning Research, Volume 12, pages 75-110, 2011.
  • P. Shivaswamy and T. Jebara. Maximum Relative Margin and Data-Dependent Regularization. Journal of Machine Learning Research, Volume 11, pages 665-706, 2010.
  • D. Lazer, A. Pentland, L. Adamic, S. Aral, A.-L. Barabasi, D. Brewer, N. Christakis, N. Contractor, J. Fowler, M. Gutmann, T. Jebara, G. King, M. Macy, D. Roy, M. Van Alstyne.  Computational Social
  • Science. Science, Volume 323, Pages 721-723, February 6, 2009.
  • C. Lima, U. Lall, T. Jebara, and A.G. Barnston.  Statistical Prediction of ENSO from Subsurface Sea Temperature Using a Nonlinear Dimensionality Reduction, Journal of Climate, Volume 22, Number 17, Pages 4501-4519, September 1, 2009.