impressions, Barbizon [jatp]

La Fenice in blu, bianco e rosso

heart of Paris

Notre Drame

Gone…! [Ash Monday]

Even stronger and farther-reaching a symbol of Paris than the Eiffel Tower, the Notre-Dame-de-Paris cathedral is now burning down. Only Hugo can make for the memory of this monumental loss:

“Sur la face de cette vieille reine de nos cathédrales, à côté d’une ride on trouve toujours une cicatrice. Tempua edax, homo edacior; ce que je traduirais volontiers ainsi: le temps est aveugle, l’homme est stupide.” Victor Hugo, Notre-Dame-de-Paris, 1831

“Notre-Dame est aujourd’hui déserte, inanimée, morte. On sent qu’il y a quelque chose de disparu. Ce corps immense est vide; c’est un squelette; l’esprit l’a quitté, on en voit la place, et voilà tout.” Victor Hugo, Notre-Dame-de-Paris, 1831

“Tous les yeux s’étaient levés vers le haut de l’église. Ce qu’ils voyaient était extraordinaire. Sur le sommet de la galerie la plus élevée, plus haut que la rosace centrale, il y avait une grande flamme qui montait entre les deux clochers avec des tourbillons d’étincelles, une grande flamme désordonnée et furieuse dont le vent emportait par moments un lambeau dans la fumée. ” Victor Hugo, Notre-Dame-de-Paris, 1831

The spire is gone. The roof is gone. What’s terrible is that it survived the French revolution, which wanted to tear it down, the 1870 siege of Paris by Prussian troops, the Commune de Paris, the 1914-1918 canon bombs from German guns, the 1944 air bombings by Allied planes. (Once again an accidental fire started by maintenance works. As in the Brazilian Museum of Natural History, Windsor Castle, Glasgow, Rennes, &tc.)

BayesComp 20 [full program]

The full program is now available on the conference webpage of BayesComp 20, next 7-10 Jan 2020. There are eleven invited sessions, including one j-ISBA session, and a further thirteen contributed sessions were selected by the scientific committee. Calls are still open for tutorials on Tuesday 07 January (with two already planed on Nimble and AutoStat) and for posters. Now is the best time for registering! Note also that travel support should be available for junior researchers.

dynamic nested sampling for stars

In the sequel of earlier nested sampling packages, like MultiNest, Joshua Speagle has written a new package called dynesty that manages dynamic nested sampling, primarily intended for astronomical applications. Which is the field where nested sampling is the most popular. One of the first remarks in the paper is that nested sampling can be more easily implemented by using a Uniform reparameterisation of the prior, that is, a reparameterisation that turns the prior into a Uniform over the unit hypercube. Which means in fine that the prior distribution can be generated from a fixed vector of uniforms and known transforms. Maybe not such an issue given that this is the prior after all.  The author considers this makes sampling under the likelihood constraint a much simpler problem but it all depends in the end on the concentration of the likelihood within the unit hypercube. And on the ability to reach the higher likelihood slices. I did not see any special trick when looking at the documentation, but reflected on the fundamental connection between nested sampling and this ability. As in the original proposal by John Skilling (2006), the slice volumes are “estimated” by simulated Beta order statistics, with no connection with the actual sequence of simulation or the problem at hand. We did point out our incomprehension for such a scheme in our Biometrika paper with Nicolas Chopin. As in earlier versions, the algorithm attempts at visualising the slices by different bounding techniques, before proceeding to explore the bounded regions by several exploration algorithms, including HMC.

“As with any sampling method, we strongly advocate that Nested Sampling should not be viewed as being strictly“better” or “worse” than MCMC, but rather as a tool that can be more or less useful in certain problems. There is no “One True Method to Rule Them All”, even though it can be tempting to look for one.”

When introducing the dynamic version, the author lists three drawbacks for the static (original) version. One is the reliance on this transform of a Uniform vector over an hypercube. Another one is that the overall runtime is highly sensitive to the choice the prior. (If simulating from the prior rather than an importance function, as suggested in our paper.) A third one is the issue that nested sampling is impervious to the final goal, evidence approximation versus posterior simulation, i.e., uses a constant rate of prior integration. The dynamic version simply modifies the number of point simulated in each slice. According to the (relative) increase in evidence provided by the current slice, estimated through iterations. This makes nested sampling a sort of inversted Wang-Landau since it sharpens the difference between slices. (The dynamic aspects for estimating the volumes of the slices and the stopping rule may hinder convergence in unclear ways, which is not discussed by the paper.) Among the many examples produced in the paper, a 200 dimension Normal target, which is an interesting object for posterior simulation in that most of the posterior mass rests on a ring away from the maximum of the likelihood. But does not seem to merit a mention in the discussion. Another example of heterogeneous regression favourably compares dynesty with MCMC in terms of ESS (but fails to include an HMC version).

[Breaking News: Although I wrote this post before the exciting first image of the black hole in M87 was made public and hence before I was aware of it, the associated AJL paper points out relying on dynesty for comparing several physical models of the phenomenon by nested sampling.]