a journal of the twice Caribean year

Read the second volume of Aliette de Bodard’s series, The House of Binding Thorns, during the Martinique trip, which proved kind of a chore, disappointingly… Visited a nice bookstore in Fort-de-France, Kazabul, which was originally twinned with La Cas’A Bulles in Cayenne that I also visited when our daughter was residing there. But did not buy any new book or local vegetables to carry home since we were bringing back some of her gear for her imminent move to Marseille for a year or so. I also read Winter’s Gift, a Rivers of London novella by Ben Aaronovitch set in… Wisconsin, with a great central character but a poor supernatural challenge and ice-thin scenario. Had a daily run around Fort-de-France without really training since the topography is just too steep for that. And a few swimming bouts in a Caribbean sea way too hot at 32⁰ to be enjoyable. Plus a catamaran excursion to the north of the island, where after missing a substantial marlin the skipper fished a yellowfin tuna that we turned into sashimi on the spot. Apart from this unique moment, and a sample of poulet boucanné from a road stall, I mostly ate local fruits, primarily bananas of various kinds. And did not sample any of the local rums despite a few visits to distilleries…

 

Natural statistical science [#2]

A rare occurrence of a Bayesian statistics paper in Nature with this “State estimation of a physical system with unknown governing equations” by Course and Nair. A variational Bayes modelling of a state system observed with noise, but without a physical model on the state (SDE) evolution itself. Which means a prior is set on a non-parametric or neural representation of the drift and a linear approximation is used for the variational approximation, leading to a Gaussian process as the approximate distribution. While this applies to highly complex models, like orbiting black holes, it is somewhat a surprise to meet this application of variational inference in a prestigious general science journal like Nature. (The picture above was taken on the train from Marseille at the end of the Bayes Fall school.)

“The approach is based on a technique called Bayesian inference, which is used widely, but which can be computationally challenging for complex systems.” B. Keith

francescoverdose [Jorge does Massilia]

off to Luminy [Autumn school in Bayesian statistics]

soon off to CIRM