## a la casa matemática de Oaxaca [reminiscence]

Posted in Mountains, Running, Travel, University life with tags , , , , , , , , , , on December 2, 2018 by xi'an

As this was my very first trip to the CMO part of CMO-BIRS, as opposed to many visits to BIRS, Banff, here are my impressions about this other mathematical haven, aka resort, aka retreat… First definitely a very loooong trip from Paris (especially when sitting next to three drunk women speaking loudly the whole trip, thankfully incomprehensibly in Russian!), with few connections between Mexico City [airport] and Oaxaca,  adding [for me] a five and a half hour stay over in the airport, where I experimented for the first time a coffin-like “sleep pod” hostel and some welcome rest. But presumably an easier access compared with Calgary for mathematicians from the South and East of the USA. And obviously for those Central and from South Americas.Then, contrary to Banff, the place for the Casa Matemàtica Oaxaca is for the time being essentially a permanently booked hotel, rather than a dedicated conference centre. Facilities are thus less attuned to visiting mathematicians, like missing real desks in bedrooms or working rooms. Still a nice with a very peaceful inner yard (and too small a pool to consider swimming). Actually facilitating interactions when compared with Banff: blackboards in the patios, tables outside, general quiet atmosphere (except for the endlessly barking dogs in the neighbourhood). Of course the huge difference in the weathers between both places does matter. Paradoxically (given the size of Oaxaca City), CMO is more isolated than BIRS, where downtown is a mere five minute walks, even in the middle of winter. Except for the occasional blizzard. But Oaxaca offers a fabulous food scene worth the longer trip!As for outdoors, there is also a swimming pool (Cina). And back streets to run on, even though the presence of stray dogs in about every road making running broken and haphazard (never run by a dog!, which is my rule since a tiny but angry dog bit my ankle in Caracas!). Running splits up hill a few times every morning was great training! There is furthermore the possibility of sport climbing in nearby San Sebastian de Tutla, as I experienced with Aventours, a local guiding company. And bouldering in an even closer gym.

## computational statistics and molecular simulation [18w5023]

Posted in pictures, Statistics, Travel, University life with tags , , , , , , , , , , , , , , , , , , , , , , , on November 14, 2018 by xi'an

On Day 2, Carsten Hartmann used a representation of the log cumulant as solution to a minimisation problem over a collection of importance functions (by the Vonsker-Varadhan principle), with links to X entropy and optimal control, a theme also considered by Alain Dunmus when considering the uncorrected discretised Langevin diffusion with a decreasing sequence of discretisation scale factors (Jordan, Kinderlehrer and Otto) in the spirit of convex regularisation à la Rockafellar. Also representing ULA as an inexact gradient descent algorithm. Murray Pollock (Warwick) presented a new technique called fusion to simulate from products of d densities, as in scalable MCMC (but not only). With an (early) starting and startling remark that when simulating one realisation from each density in the product and waiting for all of them to be equal means simulating from the product, in a strong link to the (A)BC fundamentals. This is of course impractical and Murray proposes to follow d Brownian bridges all ending up in the average of these simulations, constructing an acceptance probability that is computable and validating the output.

The second “hand-on” lecture was given by Gareth Roberts (Warwick) on the many aspects of scaling MCMC algorithms, which started with the famous 0.234 acceptance rate paper in 1996. While I was aware of some of these results (!), the overall picture was impressive, including a notion of complexity I had not seen before. And a last section on PDMPs where Gareth presented very recent on the different scales of convergence of Zigzag and bouncy particle samplers, mostly to the advantage of Zigzag.In the afternoon, Jeremy Heng presented a continuous time version of simulated tempering by adding a drift to the Langevin diffusion with time-varying energy, which must be solution to the Liouville pde $\text{div} \pi_t f = \partial_t \pi_t$. Which connects to a flow transport problem when solving the pde under additional conditions. Unclear to me was the creation of the infinite sequence. This talk was very much at the interface in the spirit of the workshop! (Maybe surprisingly complex when considering the endpoint goal of simulating from a given target.) Jonathan Weare’s talk was about quantum chemistry which translated into finding eigenvalues of an operator. Turning in to a change of basis in a inhumanly large space (10¹⁸⁰ dimensions!). Matt Moore presented the work on Raman spectroscopy he did while a postdoc at Warwick, with an SMC based classification of the peaks of a spectrum (to be used on Mars?) and Alessandra Iacobucci (Dauphine) showed us the unexpected thermal features exhibited by simulations of chains of rotors subjected to both thermal and mechanical forcings, which we never discussed in Dauphine beyond joking on her many batch jobs running on our cluster!

And I remembered today that there is currently and in parallel another BIRS workshop on statistical model selection [and a lot of overlap with our themes] taking place in Banff! With snow already there! Unfair or rather #unfair, as someone much too well-known would whine..! Not that I am in a position to complain about the great conditions here in Oaxaca (except for having to truly worry about stray dogs rather than conceptually about bears makes running more of a challenge, if not the altitude since both places are about the same).

## Canadian Rockies [jatp]

Posted in Mountains, pictures, Travel with tags , , , , , , , on August 11, 2018 by xi'an

## [summer Astrostat school] room with a view [jatp]

Posted in Mountains, pictures, R, Running, Statistics, Travel, University life with tags , , , , , , , , , , on October 9, 2017 by xi'an

I just arrived in Autrans, on the Plateau du Vercors overlooking Grenoble and the view is fabulistic! Trees have started to turn red and yellow, the weather is very mild, and my duties are restricted to teaching ABC to a group of enthusiastic astronomers and cosmologists..! Second advanced course on ABC in the mountains this year, hard to beat (except by a third course). The surroundings are so serene and peaceful that I even conceded to install RStudio for my course! Instead of sticking to my favourite vim editor and line commands.

## BIRS call for Oaxaca

Posted in Kids, Travel, University life with tags , , , , , , , on September 26, 2017 by xi'an

Here is a call for support from Nassim Goussoub, Scientific Director of BIRS:I would  like to call upon you to consider aiding the people of the State of Oaxaca. As you may know, through their support for BIRS-CMO, the people of Oaxaca have welcomed the World’s mathematical sciences community with open arms. With the plans to build a permanent facility under way, they are destined to be our hosts for years to come. I therefore ask you to contribute — if you can. Here are some of the foundations accepting donations.

1. Francisco Toledo’s Foundation, IAGO (Instituto Artes Gráficas de Oaxaca) https://www.paypal.me/donativoistmo

2. International Community Foundation(ICF) https://donate.icfdn.org/npo/international-disaster-relief-fund

3. Red Cross Mexico https://www.cruzrojamexicana.org.mx 6. Unicef Mexico https://www.unicef.org/mexico/spanish/

## O Canada! [Happy 150th birthday!]

Posted in Statistics with tags , , , , , , , , on July 1, 2017 by xi'an

I am just taking off from Paris to Montréal today for MCM 2017, on Canada Day which happens to be the 150th National Day. I have already spent three instances of a Canada Day, in both Ottawa and Banff, but this is the first in Québec and I am curious to see the atmosphere in Montréal for this occasion. If there is anything to see, since the Montréal Jazz Festival is already started…

## efficient acquisition rules for ABC

Posted in pictures, Statistics, University life with tags , , , , , , , , on June 5, 2017 by xi'an

A few weeks ago, Marko Järvenpää, Michael Gutmann, Aki Vehtari and Pekka Marttinen arXived a paper on sampling design for ABC that reminded me of presentations Michael gave at NIPS 2014 and in Banff last February. The main notion is that, when the simulation from the model is hugely expensive, random sampling does not make sense.

“While probabilistic modelling has been used to accelerate ABC inference, and strategies have been proposed for selecting which parameter to simulate next, little work has focused on trying to quantify the amount of uncertainty in the estimator of the ABC posterior density itself.”

The above question  is obviously interesting, if already considered in the literature for it seems to focus on the Monte Carlo error in ABC, addressed for instance in Fearnhead and Prangle (2012), Li and Fearnhead (2016) and our paper with David Frazier, Gael Martin, and Judith Rousseau. With corresponding conditions on the tolerance and the number of simulations to relegate Monte Carlo error to a secondary level. And the additional remark that the (error free) ABC distribution itself is not the ultimate quantity of interest. Or the equivalent (?) one that ABC is actually an exact Bayesian method on a completed space.

The paper initially confused me for a section on the very general formulation of ABC posterior approximation and error in this approximation. And simulation design for minimising this error. It confused me as it sounded too vague but only for a while as the remaining sections appear to be independent. The operational concept of the paper is to assume that the discrepancy between observed and simulated data, when perceived as a random function of the parameter θ, is a Gaussian process [over the parameter space]. This modelling allows for a prediction of the discrepancy at a new value of θ, which can be chosen as maximising the variance of the likelihood approximation. Or more precisely of the acceptance probability. While the authors report improved estimation of the exact posterior, I find no intuition as to why this should be the case when focussing on the discrepancy, especially because small discrepancies are associated with parameters approximately generated from the posterior.