Venkat Chandrasekaran

Email: alpha@beta.edu     (alpha = venkatc; beta = caltech)

Address: Annenberg 300
               California Institute of Technology
               1200 E. California Blvd.
               Mail Code 305-16
               Pasadena, CA 91125

Phone: (626) 395-6568

Brief biography

I am an Assistant Professor at Caltech in the Department of Computing and Mathematical Sciences and in the Department of Electrical Engineering.

I received a Ph.D. in Electrical Engineering and Computer Science in June 2011 from MIT, where my advisors were Professor Pablo Parrilo and Professor Alan Willsky in the Laboratory for Information and Decision Systems. I also received an S.M. in EECS in June 2007 from MIT, and a B.A. in Mathematics as well as a B.S. in Electrical and Computer Engineering in May 2005 from Rice University in Houston, Texas. I was a postdoc with Professor Michael Jordan at Berkeley during the 2011-2012 academic year.

Research interests

My current research interests broadly lie in mathematical optimization and its application to the information sciences. A particular focus is on the development of convex optimization methods for challenging problems in statistics and signal processing, with concepts from algebra and convex geometry playing prominent roles.

Publications

Journal papers

V. Chandrasekaran and M. I. Jordan, Computational and Statistical Tradeoffs via Convex Relaxation, Preprint, November 2012.

J. Saunderson, V. Chandrasekaran, P. A. Parrilo, and A. S. Willsky, Diagonal and Low-Rank Matrix Decompositions, Correlation Matrices, and Ellipsoid Fitting, Preprint, April 2012.

V. Chandrasekaran, B. Recht, P. A. Parrilo, and A. S. Willsky, The Convex Geometry of Linear Inverse Problems, Foundations of Computational Mathematics, Vol. 12, No. 6, December 2012.

V. Chandrasekaran, P. A. Parrilo, and A. S. Willsky, Convex Graph Invariants, SIAM Review, Vol. 54, No. 3, September 2012.

P. Shah and V. Chandrasekaran, Group Symmetry and Covariance Regularization, Electronic Journal of Statistics, Vol. 6, 2012.

Y. Liu, V. Chandrasekaran, A. Anandkumar, and A. S. Willsky, Feedback Message Passing for Inference in Gaussian Graphical Models, IEEE Transactions on Signal Processing, Vol. 60, No. 8, August 2012.

V. Chandrasekaran, P. A. Parrilo, and A. S. Willsky, Latent Variable Graphical Model Selection via Convex Optimization, Annals of Statistics (with discussion), Vol. 40, No. 4, August 2012. (software)

V. Chandrasekaran, M. Chertkov, D. Gamarnik, D. Shah, and J. Shin, Counting Independent Sets using the Bethe Approximation, SIAM Journal on Discrete Mathematics, Vol. 25, No. 2, July 2011.

V. Chandrasekaran, S. Sanghavi, P. A. Parrilo, and A. S. Willsky, Rank-Sparsity Incoherence for Matrix Decomposition, SIAM Journal on Optimization, Vol. 21, No. 2, June 2011.

M. J. Choi, V. Chandrasekaran, and A. S. Willsky, Gaussian Multiresolution Models: Exploiting Sparse Markov and Covariance Structure, IEEE Transactions on Signal Processing, Vol. 58, No. 5, March 2010.

V. Chandrasekaran, M. B. Wakin, D. Baron, and R. G. Baraniuk, Representation and Compression of Multi-Dimensional Piecewise Functions Using Surflets, IEEE Transactions on Information Theory, Vol. 55, No. 1, January 2009.

M. J. Choi, V. Chandrasekaran, D. M. Malioutov, J. K. Johnson, and A. S. Willsky, Multiscale Stochastic Modeling for Tractable Inference and Data Assimilation, Computer Methods in Applied Mechanics and Engineering, Vol. 297, August 2008.

V. Chandrasekaran, J. K. Johnson, and A. S. Willsky, Estimation in Gaussian Graphical Models Using Tractable Subgraphs: A Walk-Sum Analysis, IEEE Transactions on Signal Processing, Vol. 56, No. 5, May 2008.

PhD thesis

V. Chandrasekaran, Convex Optimization Methods for Graphs and Statistical Modeling, Ph.D. thesis, Massachusetts Institute of Technology, April 2011.

received the 2012 Jin-Au Kong Outstanding Dissertation Award in Electrical Engineering from MIT's Department of Electrical Engineering and Computer Science.

Selected conference papers

M. Pilanci, L. El Ghaoui, and V. Chandrasekaran, Recovery of Sparse Probability Measures via Convex Programming, Neural Information Processing Systems (NIPS 2012), Lake Tahoe, Nevada, December 2012.

V. Chandrasekaran, S. Sanghavi, P. A. Parrilo, and A. S. Willsky, Sparse and Low-Rank Matrix Decompositions, 15th IFAC Symposium on System Identification (SYSID 2009), Saint-Malo, France, July 2009.

M. J. Choi, V. Chandrasekaran, and A. S. Willsky, Exploiting Sparse Markov and Covariance Structure in Multiresolution Models, 26th Annual International Conference on Machine Learning (ICML 2009), Montreal, Canada, June 2009.

V. Chandrasekaran, N. Srebro, and P. Harsha, Complexity of Inference in Graphical Models, 24th Conference on Uncertainty in Artificial Intelligence and Statistics (UAI 2008), Helsinki, Finland, July 2008.

V. Chandrasekaran, J. K. Johnson, and A. S. Willsky, Adaptive Embedded Subgraph Algorithms using Walk-Sum Analysis, Neural Information Processing Systems (NIPS 2007), Vancouver, Canada, December 2007.

V. Chandrasekaran, J. K. Johnson, and A. S. Willsky, Maximum Entropy Relaxation for Graphical Model Selection given Inconsistent Statistics, IEEE 2007 Statistical Signal Processing Workshop (SSP 2007), Madison, Wisconsin, August 2007.

J. K. Johnson, V. Chandrasekaran, and A. S. Willsky, Learning Markov Structure by Maximum Entropy Relaxation, 11th International Conference in Artificial Intelligence and Statistics (AISTATS 2007), San Juan, Puerto Rico, March 2007.

V. Chandrasekaran, M. B. Wakin, D. Baron, and R. G. Baraniuk, Surflets: A Sparse Representation for Multidimensional Functions Containing Smooth Discontinuities, IEEE 2004 International Symposium on Information Theory (ISIT 2004), Chicago, Illinois, June 2004. (See supplemental tech report)

Technical reports

V. Chandrasekaran, N. Srebro, and P. Harsha, Complexity of Inference in Graphical Models, May 2010.

Last updated: November 2012