Journal Publications

Nicholas Ruozzi and Sekhar Tatikonda
Message-passing algorithms for quadratic minimization
Journal of Machine Learning Research, 14:2287-2314, Aug. 2013.

Nicholas Ruozzi and Sekhar Tatikonda
Message-passing algorithms: Reparameterizations and splittings
IEEE Transactions on Information Theory, vol.59, no.9, pp.5860-5881, Sept. 2013.

Dexter Kozen and Nicholas Ruozzi
Applications of metric coinduction
Logical Methods in Computer Science, 5(3:10), 2009.

Conference Publications

Somdeb Sarkhel, Deepak Venugopal, Nicholas Ruozzi, and Vibhav Gogate
Efficient Inference for Untied MLNs
26th International Joint Conference on Artificial Intelligence (IJCAI), August 2017.

Nicholas Ruozzi
A Lower Bound on the Partition Function of Attractive Graphical Models in the Continuous Case
Twntieth International Conference on Artificial Intelligence and Statistics (AISTATS), April 2017.

Kui Tang, Nicholas Ruozzi, David Belanger, and Tony Jebara
Bethe learning of graphical models via MAP decoding
Nineteenth International Conference on Artificial Intelligence and Statistics (AISTATS), May 2016.

Li Chou, Somdeb Sarkhel, Nicholas Ruozzi, and Vibhav Gogate
On parameter tying by quantization
Thirtieth Conference on Artificial Intelligence (AAAI), February 2016.

Nicholas Ruozzi
Approximate MAP inference in continuous MRFs
Advances in Neural Information Processing Systems (NIPS), December 2015.

Nicholas Ruozzi and Tony Jebara
Making pairwise binary graphical models attractive
Advances in Neural Information Processing Systems (NIPS), December 2014.
Spotlight Presentation

Nicholas Ruozzi
Beyond log-supermodularity: lower bounds and the Bethe partition function
Uncertainty in Artificial Intelligence (UAI), July 2013.

Nicholas Ruozzi
The Bethe partition function of log-supermodular graphical models
Advances in Neural Information Processing Systems (NIPS), December 2012.

Nicholas Ruozzi
Convergent message-passing in the presence of erasures
Proceedings of the 50th Annual Allerton Conference on Communication, Control, and Computing, October 2012.

Nicholas Ruozzi and Sekhar Tatikonda
Convergent and correct message-passing schemes for optimization problems
over graphical models

Presented, in part, at Uncertainty in Artficial Intelligence (UAI), 2010.

Nicholas Ruozzi and Sekhar Tatikonda
Unconstrained minimization of quadratic functions via min-sum

Proceedings of the Conference on Information Sciences and Systems (CISS), Princeton, NJ/USA, March 2010.

Nicholas Ruozzi, Justin Thaler, and Sekhar Tatikonda
Graph covers and quadratic minimization

Proceedings of the 47th Annual Allerton Conference on Communication, Control, and Computing, September 2009.

Nicholas Ruozzi and Sekhar Tatikonda
s-t paths using the min-sum algorithm

Proceedings of the 46th Annual Allerton Conference on Communication, Control, and Computing, September 2008.

Dexter Kozen and Nicholas Ruozzi
Applications of metric coinduction

In T. Mossakowski et al., editor, Proc. 2nd Conf. Algebra and Coalgebra in Computer Science (CALCO), v. 4624 of LNCS, pages 327-341. Springer, August 2007.

Thesis

Nicholas Ruozzi
Message Passing Algorithms for Optimization

Yale University, August 2011.