I just updated my short review on Bayesian computational tools I first wrote in April for the Annual Review of Statistics and Its Applications. The coverage is quite restricted, as I took advantage of two phantom papers I had started a while ago, one with Jean-Michel Marin, on hierarchical Bayes methods and on ABC. (As stressed in the first version, the paper handles missing data, not as a topic, but as a fact!) The running example is the Laplace vs. Gauss model choice problem, first considered in our ABC model choice paper. The referee of the paper was asking for a broader perspective, which makes perfect sense (except that I did not have the time to get that broad). And mentioned a potential missing acknowledgement of priority as Olli’s thesis was using a simple (instead of double) exponential vs. Gauss as its running example. Once again, a plain 25 pages introduction to the topic, not aiming at anything new. The exercise made me ponder whether or not I wanted to engage into it in a near future, with a pessimistic outcome!
Archive for computational statistics
Just yet another perfect day in Providence! Especially when I thought it was going to be a half-day: After a longer and slightly warmer run in the early morning around the peninsula, I attended the lecture by Eric Moulines on his recent results on adaptive MCMC and the equi-energy sampler. At this point, we were told that, since Peter Glynn was sick, the afternoon talks were drifted forward. This meant that I could attend Mylène Bédard’s talk in the morning and most of Xiao-Li Meng’s talk, before catching my bus to the airport, making it a full day in the end!
The research presented by Mylène (and coauthored with Randal Douc and Eric Moulines) was on multiple-try MCMC and delayed-rejection MCMC, with optimal scaling results and a comparison of the efficiency of those involved schemes. I had not seen the work before and got quite impressed by the precision of the results and the potential for huge efficiency gains. One of the most interesting tricks was to use an antithetic move for the second step, considerably improving the acceptance rate in the process. An aside exciting point was to realise that the hit-and-run solution was also open to wide time-savings thanks to some factorisation.
While Xiao-Li’s talk had connections with his earlier illuminating talk in New York last year, I am quite desolate to have missed [the most novel] half of it (and still caught my bus by a two minute margin!), esp. because it connected beautifully with the constant estimation controverse! Indeed, Xiao-Li started his presentation with the pseudo-paradox that the likelihood cannot be written as a function of the normalising constant, simply because this is not a free parameter. He then switched to his usual theme that the dominating measure was to be replaced with a substitute and estimated.The normalising constant being a function of the dominating measure, it is a by-product of this estimation step. And can even be endowed within a Bayesian framework. Obviously, one can always argue against the fact that the dominating measure is truly unknown, however this gives a very elegant safe-conduct to escape the debate about the constant that did not want to be estimated…So to answer Xiao-Li’s question as I was leaving the conference room, I have now come to a more complete agreement with his approach. And think further advances could be contemplated along this path…
Just another perfect day in Providence! After a brisk run in the eearly morning which took me through Brown campus, I attended the lecture by Sean Meyn on feedback particle filters. As it was mostly on diffusions with control terms, just too far from my field, I missed most of the points. (My fault, not Sean’s!) Then Ramon von Handel gave a talk about the curse(s) of dimensionality in particle filters, much closer to my interests, with a good summary of why (optimal) filters were not suffering from a curse in n, the horizon size, but in d, the dimension of the space, followed by an argument that some degree of correlation decay could overcome this dimensional curse as well. After the lunch break (where I thought further about the likelihood principle!), Dana Randall gave a technical talk on mixing properties of the hardcore model on Z² and bounding the cutoff parameter, which is when I appreciated the ability to follow talks from the ICERM lounge, watching slides and video of the talk taking place on the other side of the wall! At last, and in a programming contrapoint from slowly mixing to fastest mixing, Jim Fill presented his recent work on ordering Markov chains and finding fastest-mixing chains, which of course reminded me of Peskun ordering although there may be little connection in the end. The poster session in the evening had sufficiently few posters to make the discussion with each author enjoyable and relevant.A consistent feature of the meeting thus, allowing for quality interacting time between participants. I am now looking forward the final day with a most intriguing title by my friend Eric Moulines on TBA…
I have just arrived in Providence, RI, for the ICERM workshop on Performance Analysis of Monte Carlo Methods. While the plane trip was uneventful and even relaxing, as I could work on the revision to our ABCel (soon to be BCel!) paper, the bus trip from Boston to Providence, while smooth, quiet, wirelessed, and on-time, was a wee too much as it was already late for my standards… Anyway, I am giving one of the talks tomorrow, with a pot-pourri on ABC and empirical likelihood as in Ames and Chicago last month. The format of the workshop sounds very nice, with only four talks a day, which should leave a lot of space for interactions between participants (if I do not crash from my early early rise…) And, as mentioned earlier, I am looking forward visiting the futuristic building.
A large avalanche on one of the most classical routes to the summit of Mont Blanc early yesterday morning alas caught several groups climbing towards Mont Blanc and most sadly killed nine of them, including the BMC former secretary Roger Payne. It was triggered by a sérac fall above the route, always a possibility in this area whose name says it all… At a very minor level, compared with those tragic deaths, let me point out that The Guardian reported on this tragic accident with the following “bad graph”, which apparently gives the number of deaths on each accident (month?) with no consideration for the time (first axis). In other words, the barplot is missing all the zeroes. (It also missed the group of two who died from exhaustion in the Jorasses last November…)
This is not the right post to elaborate on the announcement that the next MCM’ski conference will take place in Chamonix, presumably on January 6-8, 2014. I am currently waiting for a formal proposal from the conference bureau in Chamonix… Nor on the incoming creation of a computational Bayes (BayesComp) ISBA section [if enough ISBA members support this creation].
I have just received an invitation to take part in the program “Computational Challenges in Probability” organised by ICERM (Institute for Computational and Experimental Research in Mathematics, located in what sounds like a terrific building!) next semester. Here is the purpose statement:
The Fall 2012 Semester on “Computational Challenges in Probability” aims to bring together leading experts and young researchers who are advancing the use of probabilistic and computational methods to study complex models in a variety of fields. The goal is to identify common challenges, exchange existing tools, reveal new application areas and forge new collaborative efforts. The semester includes four workshops – Bayesian Nonparametrics, Uncertainty Quantification, Monte Carlo Methods in the Physical and Biological Sciences and Performance Analysis of Monte Carlo Methods. In addition, synergistic activities will be planned throughout the duration of the semester. In particular, there will be several short courses and plenary invited talks by experts on related topics such as graphical models, randomized algorithms and stochastic networks, regular weekly seminars and relevant film screenings.
There are thus four workshops organised over the period and an impressive collection of long-term participants. I will most likely take part in the last workshop, “Performance Analysis of Monte Carlo Methods”, although I would like to attend all of them! (Interesting side remark: while looking at the ICERM website, I found that May 18th is the Day of Data! Great, except that neither the word statistitics nor the word statistician appear on the page…)
Next January 25, I will take part in a workshop at the University of Warwick, (organised by CRiSM and CSC) on the theme of GPUs in Computational Statistics. Even though I have not directly worked on GPUs, I will talk about our joint work with Pierre Jacob and Murray Smith. While Pierre will talk about Parallel Wang-Landau. From there I will travel to Cambridge for a seminar on ABC model choice the next Friday.