• S.B. (1995) Physics, MIT.
• S.M. (2003) Electrical Engineering and Computer Science, MIT.
• Ph.D (2008) Electrical Engineering and Computer Science, MIT.
• Employment:
  • 1995-2000 Member Technical Staff, Alphatech, Inc.
  • 2000-2008 Research Assistant, MIT.
  • 2008-Present Director Funded Postdoctoral Fellow, LANL.

Research Interests:

• Information theory and statistical physics.
• Statistical signal and image processing.
• Convex optimization approaches to inference and learning in graphical models.
• Multiscale approaches motivated by the multigrid method, fast-multipole algorithm and renormalization group method.

Selected Recent Publications:

1. J. Johnson, V. Chernyak and M. Chertkov. Orbit-Product Representation and Correction of Gaussian Belief Propagation. To appear Inter. Conf. on Machine Learning, June 2009.
2. J. Johnson, D. Bickson and D. Dolev. Fixing Convergence of Gaussian Belief Propagation. To appear Inter. Symposium on Information Theory, June 2009.
3. J. Johnson, Convex Relaxation Methods for Graphical Models: Lagrangian and Maximum Entropy Approaches. Ph.D Thesis. MIT, Aug. 2008.
4. J. Johnson and A. Willsky. A Recursive Model-Reduction Method for Estimation in Gaussian Markov Random Fields. IEEE Trans. on Image Processing, Jan. 2008.
5. J. Johnson, D. Malioutov and A. Willsky. Lagrangian relaxation method for MAP estimation in graphical models. In Allerton Conf. on Communication, Control and Computing, Sep. 2007.
6. J. Johnson, V. Chandrasekaran and A. Willsky. Learning Markov Structure by Maximum Entropy Relaxation. In Inter. Conf. on AI and Statistics, March 2007.
7. J. Johnson, D. Malioutov and A. Willsky. Walk-Sum Interpretation and Analysis of Gaussian Belief Propagation. Adv. Neural Information Processing, Dec. 2005.