There will be another i-like workshop this Spring, over two days in Oxford, St Anne’s College, involving talks by Xiao-Li Meng and Eric Moulines, as well as by researchers from the participating universities. Registration is now open. (I will take part as a part-time participant, travelling from Nottingham where I give a seminar on the 20th.)
Archive for i-like
As a few more weeks have gone since I left the hospital, here are some news for the aficionadi (apulgaradi?). The wound on the thumb is healing at a good pace, although the dressings are still on for one or two weeks. While I am still recovering from those weeks in the hospital, lacking energy at times (and getting quickly tired by metro rides), the only major after-effect is an intolerance to beer. Hopefully temporary! I managed to get back to an almost daily run in the nearby park (and to lose my camera, again!, in the process). Once again, most sincere thanks to all of you who sent and keep sending me greetings and good wishes, incl. special thanks to my friends in the Statistics department at QUT for their collective postcard [and yes they can laugh about ït]! And to friends from New York who called me several times. Although my scientific production is very limited at the moment, since the i-like workshop was both enjoyable and cathartic, I plan to attend the French statistical meeting next week in Toulouse [hopefully getting some kg back from the great South-West cuisine!], followed by ABC in Roma [another opportunity for great food]. On the following weekend, I should leave for Vietnam to give a course on Bayesian analysis and attend a conference as well.
Indeed, I liked the i-like workshop very much. Among the many interesting talks of the past two days (incl. Cristiano Varin’s ranking of Series B as the top influential stat. journal!) , Matti Vihola’s and Nicolas Chopin’s had the strongest impact on me (to the point of scribbling in my notebook). In a joint work with Christophe Andrieu, Matti focussed on evaluating the impact of replacing the target with an unbiased estimate in a Metropolis-Hastings algorithm. In particular, they found necessary and sufficient conditions for keeping geometric and uniform ergodicity. My question (asked by Iain Murray) was whether they had derived ways of selecting the number of terms in the unbiased estimator towards maximal efficiency. I also wonder if optimal reparameterisations can be found in this sense (since unbiased estimators remain unbiased after reparameterisation).
Nicolas’ talk was about particle Gibbs sampling, a joint paper with Sumeet Singh recently arXived. I did not catch the whole detail of their method but/as I got intrigued by a property of Marc Beaumont’s algorithm (the very same algorithm used by Matti & Christophe). Indeed, the notion is that an unbiased estimator of the target distribution can be found in missing variable settings by picking an importance sampling distribution q on those variables. This representation leads to a pseudo-target Metropolis-Hastings algorithm. In the stationary regime, there exists a way to derive an “exact” simulation from the joint posterior on (parameter,latent). All the remaining/rejected latents are then distributed from the proposal q. What I do not see is how this impacts the next MCMC move since it implies generating a new sample of latent variables. I spoke with Nicolas about this over breakfast: the explanation is that this re-generated set of latent variables can be used in the denominator of the Metropolis-Hastings acceptance probability and is validated as a Gibbs step. (Incidentally, it may be seen as a regeneration event as well.)
Furthermore, I had a terrific run in the rising sun (at 5am) all the way to Kenilworth where I was a deer, pheasants and plenty of rabbits. (As well as this sculpture that now appears to me as being a wee sexist…)