Archive for the Travel Category

métro static

Posted in pictures, Travel with tags , , on February 8, 2016 by xi'an

gare RER de Sceaux, May14, 2012[During a particularly painful métro trip, a man kept talking and talking in a very aggressive and somewhat incoherent manner. It is not until the end of the ride that I realised he was speaking on the phone to a relative… and not to an inexistent other self!]

“Vous voulez me faire jouer un rôle hein mais ca ne marche pas avec moi, vous jouez tous des rôles, la journée finie, vous rentrez chez vous, vous vous démaquillez, vous enlevez vos masques. Plutôt vous avez deux masques, un pour la journée et un pour le soir, le vrai et le faux, le faux c’est celui de la journée.”

Bayesian model comparison with intractable constants

Posted in Books, Kids, pictures, Statistics, Travel, University life with tags , , , , , , , , , , , on February 8, 2016 by xi'an

abcIRichard Everitt, Adam Johansen (Warwick), Ellen Rowing and Melina Evdemon-Hogan have updated [on arXiv] a survey paper on the computation of Bayes factors in the presence of intractable normalising constants. Apparently destined for Statistics and Computing when considering the style. A great entry, in particular for those attending the CRiSM workshop Estimating Constants in a few months!

A question that came to me from reading the introduction to the paper is why a method like Møller et al.’s (2006) auxiliary variable trick should be considered more “exact” than the pseudo-marginal approach of Andrieu and Roberts (2009) since the later can equally be seen as an auxiliary variable approach. The answer was on the next page (!) as it is indeed a special case of Andrieu and Roberts (2009). Murray et al. (2006) also belongs to this group with a product-type importance sampling estimator, based on a sequence of tempered intermediaries… As noted by the authors, there is a whole spectrum of related methods in this area, some of which qualify as exact-approximate, inexact approximate and noisy versions.

Their main argument is to support importance sampling as the method of choice, including sequential Monte Carlo (SMC) for large dimensional parameters. The auxiliary variable of Møller et al.’s (2006) is then part of the importance scheme. In the first toy example, a Poisson is opposed to a Geometric distribution, as in our ABC model choice papers, for which a multiple auxiliary variable approach dominates both ABC and Simon Wood’s synthetic likelihood for a given computing cost. I did not spot which artificial choice was made for the Z(θ)’s in both models, since the constants are entirely known in those densities. A very interesting section of the paper is when envisioning biased approximations to the intractable density. If only because the importance weights are most often biased due to the renormalisation (possibly by resampling). And because the variance derivations are then intractable as well. However, due to this intractability, the paper can only approach the impact of those approximations via empirical experiments. This leads however to the interrogation on how to evaluate the validity of the approximation in settings where truth and even its magnitude are unknown… Cross-validation and bootstrap type evaluations may prove too costly in realistic problems. Using biased solutions thus mostly remains an open problem in my opinion.

The SMC part in the paper is equally interesting if only because it focuses on the data thinning idea studied by Chopin (2002) and many other papers in the recent years. This made me wonder why an alternative relying on a sequence of approximations to the target with tractable normalising constants could not be considered. A whole sequence of auxiliary variable completions sounds highly demanding in terms of computing budget and also requires a corresponding sequence of calibrations. (Now, ABC fares no better since it requires heavy simulations and repeated calibrations, while further exhibiting a damning missing link with the target density. ) Unfortunately, embarking upon a theoretical exploration of the properties of approximate SMC is quite difficult, as shown by the strong assumptions made in the paper to bound the total variation distance to the true target.

Eagle and Child

Posted in Books, Kids, pictures, Travel, University life, Wines with tags , , , , , , on February 4, 2016 by xi'an

a glacial PhD in Iceland [job announcement]

Posted in Kids, Mountains, pictures, Statistics, Travel, University life with tags , , , , , , on February 3, 2016 by xi'an

[Here is a PhD offer at the University of Iceland that may be of interest to some readers or their students. I would have been interested 30 years ago!]

The Department of Mathematics at the University of Iceland (UI) seeks applicants for a fully funded 3 year PhD position for the project Statistical Models for Glaciology.

The student will develop Bayesian hierarchical spatio-temporal models to the field of glaciology, working with a consortium of experts at the University of Iceland, the University of Missouri and the Norwegian University of Science and Technology. The key people in the consortium are Prof. Birgir Hrafnkelsson at UI, Prof. Chris Wikle, and Prof. Håvard Rue, experts in spatial statistics and Bayesian computation. Another key person is Prof. Gudfinna Adalgeirsdottir at UI, an expect in glaciology. The Glaciology group at UI possesses extensive data and knowledge about the Icelandic glaciers.

The application deadline is February 29, 2016.

Detailed project description

Job ad with information on how to apply:

Oxford snapshot

Posted in pictures, Running, Travel, University life with tags , , , on February 2, 2016 by xi'an

internships for midnight sun [2016]

Posted in Kids, pictures, Statistics, Travel, University life with tags , , , on February 1, 2016 by xi'an

[Aki Vehtari asked me to post this announcement for internships next summer at Aalto Science Institute, Otaniemi, Finland. Otaniemi is around 10 km from Helsinki.]

The Aalto Science Institute internships program offers undergraduate students(at BSc level) the opportunity to participate first-hand in topical research,to interact with the premier research groups at Aalto University, and to network in an international environment. Positions are available in several fields of study ranging from nanotechnology and semiconductors to machine learning, data communications and human-computer interaction. AScI interns are usually hired for three months, and the typical training period is from 01 June until 31 August. The interns are employed by the departments of the School of Science and the School of Electrical Engineering, and the exact timing of the internship may be agreed with the hosting department. The incoming students are mentored throughout the stay by one of the professors affiliated with AScI. The priority for incoming AScI-internship positions is given to students who have not yet been studying or working at Aalto. AScI internship students will receive a salary which is sufficient to cover living costs such as accommodation. The salary is determined based on experience and qualifications according to the salary system of Aalto University for student interns. Minimum internship salary is 1450 €/ month.

Deadline for applications is 18 February 2016.

off to Oxford

Posted in Kids, pictures, Travel, University life with tags , , , , , , , on January 31, 2016 by xi'an

Oxford, Feb. 23, 2012I am off to Oxford this evening for teaching once again in the Bayesian module of the OxWaSP programme. Joint PhD programme between Oxford and Warwick, supported by the EPSRC. And with around a dozen new [excellent!] PhD students every year. Here are the slides of a longer course that I will use in the coming days:

And by popular request (!) here is the heading of my Beamer file:

\documentclass[xcolor=dvipsnames,professionalfonts]{beamer}
\usepackage{colordvi}
\usetheme{Montpellier}
\usecolortheme{beaver}
% Rather be using my own color
\definecolor{LightGrey}{rgb}{0.84,0.83,0.83}
\definecolor{LightYell}{rgb}{0.90,0.83,0.70}
\definecolor{StroYell}{rgb}{0.95,0.88,0.72}
\definecolor{myem}{rgb}{0.797,0.598,0.598}
\definecolor{lightred}{rgb}{0.75,0.033,0}
\definecolor{shadecolor1}{rgb}{0.90,0.83,0.70}
\setbeamercovered{transparent=20}
\setbeamercolor{structure}{fg=myem!120}
\setbeamercolor{alerted text}{fg=lightred}
\setbeamertemplate{blocks}[rounded][shadow=true]
Follow

Get every new post delivered to your Inbox.

Join 981 other followers