Archive for Valencia 9

Climbing in Sella

Posted in Mountains, Travel with tags , , , on June 7, 2010 by xi'an

A bonus—on top of attending the meeting of course!—in coming to Benidorm for the València 9 meeting was to go climbing on one of the numerous routes nearby. While the cliffs of Peñon de Ifach were most attractive, the lack of clear information on the fully bolted routes led me to pick the backcountry cliffs near Sella, where Julien Cornebise and I climbed a 30m V+ route called via del indio. We were actually quite lucky in that the cliff was already visited by local climbers who were quite helpful: as I got stuck on a hidden hand hold when lead-climbing, one of them went up to equip the whole route for us. (Although this was a muy fàcil V+ route, I think I would have had even more difficuties with the final stretch before the belay!) Once equipped, the route indeed felt like a V+ and we spent the next hours going up and down until it was time to get back to the talks. The cliff was facing south/south-west and hence very exposed but between the breeze and the passing clouds it was quite tolerable. And the views on the surrounding red cliffs was amazing.

València 9 snapshot [3]

Posted in Statistics, University life with tags , , , , on June 7, 2010 by xi'an

Today was somehow a low-key day for me in terms of talks as I was preparing a climb in the Benidorm backcountry (thanks to the advice of Alicia Quiròs) and trying to copy routes from the (low oh so low!) debit wireless at the hotel. The session I attended in the morning was on Bayesian non-parametrics, with David Dunson giving a talk on non-parametric classification, a talk whose contents were so dense in information that it felt like three talks rather than one, especially when there was no paper to back it up! Katja Ickstadt modelled graphical dependence structures using non-parametrics but also mixtures of normals across different graph structures, an innovation I found interesting if difficult to interpret. Tom Loredo concluded the session with a broad and exciting picture of the statistical challenges found in spectral astronomy (even though I often struggle to make sense of the frequency data astronomers favour).

The evening talk by Ioanna Manolopoulou was a superbly rendered study on cell dynamics with incredible 3D animations of those cell systems, representing the Langevin diffusion on the force fields in those systems as evolving vector fields. And then I gave my poster on the Savage-Dickey paradox, hence missing all the other posters in this session… The main difficulty in presenting the result was not about the measure-theoretic difficulty, but rather in explaining the Savage-Dickey representation since this was unknown to most passerbys.

On particle learning

Posted in R, Statistics, University life with tags , , on June 5, 2010 by xi'an

In connection with the Valencia 9 meeting that started yesterday, and with Hedie‘s talk there, we have posted on arXiv a set of comments on particle learning. The arXiv paper contains several discussions but they mostly focus on the inevitable degeneracy that accompanies particle systems. When Lopes et al. state that p(Z^t|y^t) is not of interest as the filtered, low dimensional p(Z_t|y^t) is sufficient for inference at time t, they seem to implicitly imply that the restriction of the simulation focus to a low dimensional vector is a way to avoid the degeneracy inherent to all particle filters. The particle learning algorithm therefore relies on an approximation of p(Z^t|y^t) and the fact that this approximation quickly degenerates as t increases means that this approximation impacts the approximation of p(Z_t|y^t). We show that, unless the size of the particle population exponentially increases with t, the sample of Z_t‘s will not be distributed as an iid sample from p(Z_t|y^t).

The graph above is an illustration of the degeneracy in the setup of a Poisson mixture with five components and 10,000 observations. The boxplots represent the variation of the evidence approximations based on a particle learning sample and Lopes et al. approximation, on a particle learning sample and Chib’s (1995) approximation, and on an MCMC sample and Chib’s (1995) approximation, for 250 replications. The differences are therefore quite severe when considering this number of observations. (I put the R code on my website for anyone who wants to check if I programmed things wrong.) There is no clear solution to the degeneracy problem, in my opinion, because the increase in the particle size overcoming degeneracy must be particularly high… We will be discussing that this morning.