Tractable Inference for Probabilistic Models by Free Energy Approximations

author: Manfred Opper, Department of Artificial Intelligence, TU Berlin
published: Feb. 25, 2007,   recorded: September 2004,   views: 4513

Related Open Educational Resources

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.


Probabilistic models explain complex observed data by a set of unobserved, hidden random variables based on the joint distribution of the variables. Statistical inference requires the evaluation of high dimensional sums or integrals. Hence, one has to deal with a vast computational complexity when the number of hidden variables is large and it is important to develop tractable approximations. I will discuss ideas for such approximations which are based on a variational formulation of inference. Quantities of interest, like marginal moments of the distribution are found as minima of an entropic quantity, often called the Gibbs Free Energy. While an exact computation of the Free Energy is computationally intractable, sensible approximations often provide quite accurate results. I will discusss applications of these techniques to the estimation of wind fields from satellite measurements, to a model of an error correcting code in telecommunication and to approximate resampling methods.

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Write your own review or comment:

make sure you have javascript enabled or clear this field: