multicanonical sampling

Add to your list(s) Download to your calendar using vCal

• Ole Winther, IMM, DTU and Inference Group
• Thursday 07 July 2005, 11:30-12:30
• Jasmine Room, Microsoft Research Cambridge.

If you have a question about this talk, please contact David MacKay.

In multicanonical ensemble and other artificial ensemble Monte Carlo methods one samples from from a distribution different than the canonical (the true posterior distribution) in order to make the relaxation of the Markov chain more effective. I will lead a discussion of some of these techniques and try to indicate that they actually involve inference problems.

The presentation will be based upon the review in Jesper Ferkinghoff-Borg’s thesis, available from http://www.nbi.dk/~borg/

This talk is part of the Machine Learning Journal Club series.

This talk is included in these lists:

• Cambridge talks
• Guy Emerson's list
• Hanchen DaDaDash
• Inference Group Journal Clubs
• Inference Group Summary
• Interested Talks
• Jasmine Room, Microsoft Research Cambridge
• ML
• Machine Learning Journal Club
• Machine Learning Summary
• Quantum Matter Journal Club
• TQS Journal Clubs
• rp587
• yk373's list

Note that ex-directory lists are not shown.