Jonathan S. Yedidia
Phone: 617-621-7544
Email: yedidia at merl dot com
Official web page: http://www.merl.com/people/yedidia/
My Blog: Nerd Wisdom
Complete list of Jonathan Yedidia's MERL Technical Reports
Complete list of Jonathan Yedidia's Publications since 2000
Research Overview
Most of my current research
involves the application of statistical methods to "inference" problems.
Some important fields which are dominated by the issue of
inference are computer vision, speech recognition, natural language
processing, error-control coding and digital communications.
Essentially, any time you are receiving a noisy
signal, and need to infer
what is really out there, you are dealing with an inference problem.
A productive way to
deal with an inference problem is to formalize it as a problem of computing
probabilities in a graphical model. Graphical models, which are
referred to in various guises as "Markov random fields," "Bayesian networks,"
or "factor graphs," provide a statistical
framework to encapsulate our knowledge of
a system and to infer from incomplete information.
Physicists who use the
techniques of
statistical mechanics to study the behavior of
disordered magnetic spin systems are actually studying a mathematically
equivalent problem to the inference problem studied by
computer scientists or electrical engineers, but with different
terminology, goals, and perspectives. My own research has focused on the
surprising
relationships between methods that are used in these communities, and
on powerful new techniques and algorithms that exploit those relationships.
Physics publications from 1992 and before
J.S. Yedidia,
Spin Glasses, Vortex Glasses, and Other Glasses, chapter in "1992
Lectures on Complex Systems" (Santa Fe Institute Studies in the Sciences
of Complexity), ed. by L. Nadel and D. Stein. Some people find these
lectures useful, especially as a tutorial on the replica method:
Postscript,PDF)
J.P. Bouchaud, M. Mézard, and J.S. Yedidia, A Variational Theory for the Pinning of Vortex Lattices by Impurities, Physical
Review B 46, 14686-14701, 1992.
J.P. Bouchaud, M. Mézard, and J.S. Yedidia,
Variational Theory for Disordered Vortex Lattices, Physical
Review Letters 67, 3840-3843, 1991.
J.P. Bouchaud, M. Mézard, and J.S. Yedidia,
Some Mean-field-like equations Describing the Folding of Heteropolymers
at Finite Temperature, Proceedings of the 1991 Elba Conference on
Biophysics.
J.P. Bouchaud, M. Mézard, G. Parisi,
and J.S. Yedidia, Polymers with Long-ranged Self-repulsion: a
Variational Approach, Journal of Physics A Letters L1025-L1030, 1991.
A. Georges and J.S. Yedidia,
How to Expand Around Mean-field Theory Using High-temperature Expansions,
Journal of Physics A 24 2173-2192, 1991.
A. Georges and J.S. Yedidia,
Onsager Reaction Terms for Quantum Many-Body Systems: Application to
Antiferromagnetic and Superconducting Order in the Hubbard Model,
Physical Review B43, 3475-3482, 1991.
A. Georges, M. Mézard, and J.S. Yedidia,
Low-temperature Phase of the Ising Spin Glass on a Hypercubic Lattice,
Physical Review Letters 64, 2937-2940, 1990.
J.S. Yedidia,
Thermodynamics of the Infinite-U Hubbard Model,
Physical Review B41, 9397-9402, 1990.
J.S. Yedidia and A. Georges,
The Fully Frustrated Ising Model in Infinite Dimensions,
Journal of Physics A 23, 2165-2171, 1990.
J.S. Yedidia,
Neural Networks that use Three-state Neurons,
Journal of Physics A 22, 2265-2273, 1989.