Picture from my MIT student ID.

Jason K. Johnson

PhD, EECS Dept., MIT.
Stochastic Systems Group (SSG),
Laboratory for Information and Decision Systems (LIDS).


I completed the PhD program in 2008 and am now a director-funded postdoctoral fellow working with Michael Chertkov at Los Alamos National Laboratory, Center for Nonlinear Studies and Theoretical Division T-4. Please see my current CNLS webpage for recent publications.

Brief Biography

I attended Appalachian State University for two years before transferring to MIT, where I graduated S.B. Physics, 1995. During the next five years, I was a member of technical staff with Alphatech Inc., where I helped develop algorithms for multi-resolution signal and image processing, data fusion and multi-target tracking. In 2000, I entered the EECS graduate program at MIT under the direction of Alan Willsky, where I earned the S.M., 2003, and am currently working to complete the PhD program.

Research Summary

My research has focused on the use of information theory and convex optimization to provide principled, tractable approximation methods for solving large-scale inference and estimation problems involving graphical models, also known as Markov random fields (MRFs). In particular, Gaussian MRFs (commonly used in image processing) have played a central role in these investigations.

Here are summaries of several novel methods that I introduced:

Teaching Experience

TA for 6.867 Introduction to Machine Learning, Fall 2003.


Publications and Selected Talks

Message-Passing Algorithms for GMRFs and Non-Linear Optimization (Invited talk). NIPS Workshop on Approximate Bayesian Inference in Continuous/Hybrid Models. Whistler B.C., Canada. December 7, 2007.

Recursive Cavity Modeling

Maximum-Entropy Relaxation

Lagrangian Relaxation

See also this related technical note:


Other Publications

Unpublished Papers and Technical Notes

Last updated: December 13, 2010.
Number of Visitors (since 2/07):