Banff worshop [BIRS 12w5105 meeting]

The workshop 12w5105 at BIRS, Banff, has now started for good! To wit, we had the customary group photo outside the TransCanada Pipeline Pavilion where BIRS is now hosted. (With Mount Rundle as a guest star!) The first day saw talks by or on physics, astrophysics, and genetics. In particular, Dawn Woodard gave a particularly stimulating talk on the fine convergence analysis of Liu et al.’s (1995) seminal Gibbs algorithm: The most striking result related to an exponential decay in the spectral gap with the number of observations þ when the entropy is multimodal and the Markov chain jumps are also decreasing exponentially with þ. (As usual, I had trouble relating to the physics talks, more because of the vocabulary and of the focus than because of the contents… They sounded quite exciting, though, in their connections with correlated sampling and simulated annealing.) Here are the slides of my talk for tomorrow.

3 Responses to “Banff worshop [BIRS 12w5105 meeting]”

  1. […] in the project (on which I mostly spent an Amsterdam/Calgary flight and jet-lagged nights at BIRS…), even though I got excited by finding the bits and pieces about Bayesian estimation and […]

  2. […] I left Banff in the early afternoon of Thursday, I only attended the morning session of the BIRS 12w5105 workshop (just like yesterday since there was a free afternoon!). Yesterday morning, Gareth Roberts […]

  3. Je t’ai trouvé ! Trop mignon :)

Leave a comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.