David Sontag's Home Page

I am an Assistant Professor in NYU's Computer Science department. My research focuses on theoretical and practical aspects of machine learning and probabilistic inference, with recent applications to medicine, natural language processing, and information retrieval. My group has a close collaboration with the Emergency Medicine Informatics Research Lab at Beth Israel Deaconess Medical Center.

I am looking for students! Please consider applying to our PhD program.

Most recently I was a post-doc at Microsoft Research New England. My Ph.D. is in Computer Science from MIT, where I worked with Tommi Jaakkola on approximate inference and learning in probabilistic models. My bachelors degree is from UC Berkeley, in Computer Science, where I worked with Stuart Russell's First-Order Probabilistic Logic group.

Teaching

Publications

Theses:

• D. Sontag. Approximate Inference in Graphical Models using LP Relaxations. Ph.D. thesis, Massachusetts Institute of Technology, 2010. George M. Sprowls Award for the best doctoral theses in Computer Science at MIT (2010). BibTex
• D. Sontag. Cutting Plane Algorithms for Variational Inference in Graphical Models. Master's thesis, Massachusetts Institute of Technology, 2007. BibTex
  

  Machine learning:

  Download optimized code implementing our UAI '08 paper (see readme file).
  
  
• D. Sontag, K. Collins-Thompson, P. N. Bennett, R. W. White, S. Dumais, B. Billerbeck. Probabilistic Models for Personalizing Web Search. Fifth ACM International Conference on Web Search and Data Mining (WSDM), Feb. 2012. [Slides] BibTex
• D. Sontag, D. Roy. Complexity of Inference in Latent Dirichlet Allocation. Neural Information Processing Systems (NIPS) 25, Dec. 2011. [Slides] BibTex
• K. Collins-Thompson, P. N. Bennett, R. W. White, S. de la Chica, D. Sontag. Personalizing Web Search Results by Reading Level. Twentieth ACM International Conference on Information and Knowledge Management (CIKM 2011), Oct. 2011. BibTex
• D. Sontag, A. Globerson, T. Jaakkola. Introduction to Dual Decomposition for Inference. Optimization for Machine Learning, editors S. Sra, S. Nowozin, and S. J. Wright: MIT Press, 2011. BibTex
• D. Sontag, O. Meshi, T. Jaakkola, A. Globerson. More data means less inference: A pseudo-max approach to structured learning. Neural Information Processing Systems (NIPS) 24, Dec. 2010. Supplementary BibTex
• T. Koo, A. Rush, M. Collins, T. Jaakkola, and D. Sontag. Dual Decomposition for Parsing with Non-Projective Head Automata. Empirical Methods in Natural Language Processing (EMNLP), 2010. Best paper award. BibTex
• A. Rush, D. Sontag, M. Collins, and T. Jaakkola. On Dual Decomposition and Linear Programming Relaxations for Natural Language Processing. Empirical Methods in Natural Language Processing (EMNLP), 2010. BibTex
• O. Meshi, D. Sontag, T. Jaakkola, A. Globerson. Learning Efficiently with Approximate Inference via Dual Losses. 27th International Conference on Machine Learning (ICML), July 2010. BibTex
• T. Jaakkola, D. Sontag, A. Globerson, M. Meila. Learning Bayesian Network Structure using LP Relaxations. 13th International Conference on Artificial Intelligence and Statistics (AI-STATS), 2010. BibTex
• D. Sontag, T. Jaakkola. Tree Block Coordinate Descent for MAP in Graphical Models. 12th International Conference on Artificial Intelligence and Statistics (AI-STATS), April 2009. BibTex
• D. Sontag, A. Globerson, T. Jaakkola. Clusters and Coarse Partitions in LP Relaxations. Neural Information Processing Systems (NIPS) 21, Dec. 2008. BibTex
• D. Sontag, T. Meltzer, A. Globerson, Y. Weiss, T. Jaakkola. Tightening LP Relaxations for MAP using Message Passing. Uncertainty in Artificial Intelligence (UAI) 24, July 2008. Best paper award. BibTex
• D. Sontag, T. Jaakkola. New Outer Bounds on the Marginal Polytope. Neural Information Processing Systems (NIPS) 20, Dec. 2007. Outstanding student paper award. BibTex
  

  Computer networking:

• D. Sontag, Y. Zhang, A. Phanishayee, D. Andersen, D. Karger. Scaling All-Pairs Overlay Routing. Fifth ACM International Conference on emerging Networking EXperiments and Technologies (CoNEXT), Dec. 2009. Code BibTex
  

  Computational biology:

• D. Sontag, R. Singh, B. Berger. Probabilistic Modeling of Systematic Errors in Two-Hybrid Experiments. Pacific Symposium on Biocomputing (PSB), 2007. Supplementary information BibTex
  

  First-Order Probabilistic Logic:

• B. Milch, B. Marthi, S. Russell, D. Sontag, D. L. Ong, and A. Kolobov. BLOG: Probabilistic Models with Unknown Objects. In Lise Getoor and Ben Taskar, eds. Statistical Relational Learning. Cambridge, MA: MIT Press, 2007.
• B. Milch, B. Marthi, S. Russell, D. Sontag, D. L. Ong, and A. Kolobov. BLOG: Probabilistic Models with Unknown Objects. Proc. 19th International Joint Conference on Artificial Intelligence (IJCAI): 1352-1359, 2005. BibTex
• B. Milch, B. Marthi, D. Sontag, S. Russell, D. L. Ong, and A. Kolobov. Approximate Inference for Infinite Contingent Bayesian Networks. 10th International Workshop on Artificial Intelligence and Statistics, 2005. BibTex