sweet 60’s

The traditional group picture at the end of Eric Moulines’ 60th anniversary celebration, at IHP, Paris. Some of the participants had already left (and I am carefully hidding in the background). Among the celebrating talks reflecting the huge thematic diversity of EM’s carreer, Patrick Flandrin gave a great historical account of a certain Édouard-Léon Scott de Martinville and his invention of a sound recording device that did not meet with the same success as the later phonograph by Edison. A song he had registered in 1860 was retrieved in 2008 by a team of the Lawrence Berkeley National Laboratory, making it the earliest known intelligible voice recording in existence! Jean-François Cardoso explained how the team at Institut d’Astrophysique de Paris produced a near optimal estimate of the Cosmic Microwave Background (CMB) by linear projections preserving normality. Sara Filippi exposed a variational Bayes approach to selecting groups of variables in a GLM. Gareth Roberts illustrated retrospective sampling with his recent foray with Jeff Rosenthal in the lack of uniformity in the FIFA World Cup draws. Anatoli Iouditski spoke about a recent work on polyhedral estimation in statistical linear inverse problems. And Elisabeth Gassiat strolled through recent works on inference for hidden Markov models, including one at NeurIPS 2021 with Aapo Hyvärinen and others on nonlinear ICA. This was quite a fun meeting, with plenty of anecdotes and a few older pictures (even though I could not find any prior to 2005, which may have been the year I bought my first digital camera!)

23w5106 [group picture]

Siem Reap conference

As I returned from the conference in Siem Reap. on a flight avoiding India and Pakistan and their [brittle and bristling!] boundary on the way back, instead flying far far north, near Arkhangelsk (but with nothing to show for it, as the flight back was fully in the dark), I reflected how enjoyable this conference had been, within a highly friendly atmosphere, meeting again with many old friends (some met prior to the creation of CREST) and new ones, a pleasure not hindered by the fabulous location near Angkor of course. (The above picture is the “last hour” group picture, missing a major part of the participants, already gone!)

Among the many talks, Stéphane Shao gave a great presentation on a paper [to appear in JASA] jointly written with Pierre Jacob, Jie Ding, and Vahid Tarokh on the Hyvärinen score and its use for Bayesian model choice, with a highly intuitive representation of this divergence function (which I first met in Padua when Phil Dawid gave a talk on this approach to Bayesian model comparison). Which is based on the use of a divergence function based on the squared error difference between the gradients of the true log-score and of the model log-score functions. Providing an alternative to the Bayes factor that can be shown to be consistent, even for some non-iid data, with some gains in the experiments represented by the above graph.

Arnak Dalalyan (CREST) presented a paper written with Lionel Riou-Durand on the convergence of non-Metropolised Langevin Monte Carlo methods, with a new discretization which leads to a substantial improvement of the upper bound on the sampling error rate measured in Wasserstein distance. Moving from p/ε to √p/√ε in the requested number of steps when p is the dimension and ε the target precision, for smooth and strongly log-concave targets.

This post gives me the opportunity to advertise for the NGO Sala Baï hostelry school, which the whole conference visited for lunch and which trains youths from underprivileged backgrounds towards jobs in hostelery, supported by donations, companies (like Krama Krama), or visiting the Sala Baï  restaurant and/or hotel while in Siem Reap.

 

LMS Invited Lecture Series / CRISM Summer School 2018

O’Bayes 2017 group photograph