A fellow coder shared with me this recent manual (in French) entitled python (for the computer language, not the snake) written by Nathalie Azoulai  as he found it an interesting literary (if not computer) program. It parses rather quickly and I compiled it in one single run on my way to Bristol [Mecca of punched card coders!] last week. The core idea of this manual is one of a middle-aged, clueless (about coding), single-mother, writer engaging into an experiment to understand coding and coders. She does not succeed. And the manual also fails to implement said idea, at least for me. This ..read more

Sirio Legramanti, Daniele Durante, and Pierre Alquier just arXived a massive paper on the concentration of discrepancy–based ABC posteriors via Rademacher complexity, which includes MMD and Wasserstein distance-based ABC methods. The paper provides sufficient conditions under which a discrepancy within the integral probability semimetrics class guarantees uniform convergence and concentration of the induced ABC posterior, without necessarily requiring suitable regularity conditions for the underlying data generating process and the assumed statistical model, meaning that they also cover misspe ..read more

arXiv is now testing a new display of papers in html format to increase accessibility [for those with no pdf reader?] Hopefully, this will not induce further constraints on the LaTeX format of arXiv submissions, at a time when it got easier for off-the-shelf files to be immediately accepted, but the fact that the site encourages using Overleaf is not that promising… (The plea that readers do not create reports that the HTML paper doesn’t look exactly like the PDF paper is hilarious, as I presume many complained of exactly this drawback ..read more

A rather strange incident occurred to me this morn as I was optimising my backpack for my trip to Bristol. I found inside a stash of credit card receipts along with a booklet of down-town Paris metro tickets. As I hardly ever keep credit card receipts, I was rather surprised at it and, looking through them, the more because I could not place these purchases, although they mostly were spent in the neighbourhood of the former INSEE building in Malakoff. Checking further at the end digits of the credit card, I realised these were not agreeing with mine and thus that they had mysteriously ended u ..read more

Just recently, I came across this representation of the (global) temperature rise over the period 1850-2020, made by Professor Ed Hawkins from the University of Reading. It is powerful, artsy, reminding me of the Everything mural in the Zeeman Building at the University of Warwick, and visually most appealing, as a poster about the urgency for action, but it nonetheless remain a poor statistical graph in that it is a 2d presentation of a 1d dataset, the time series of the yearly average temperatures, missing the opportunity to exploit the second axis by eg taking a stripe of the Earth from Sou ..read more

..read more

Yesterday, which proved an unseasonal bright, warm, day, I biked (with a new wheel!) to the east of Paris—in the Gare de Lyon district where I lived for three years in the 1980’s—to attend a Mokaplan seminar at INRIA Paris, where Anna Korba (CREST, to which I am also affiliated) talked about sampling through optimization of discrepancies. This proved a most formative hour as I had not seen this perspective earlier (or possibly had forgotten about it). Except through some of the talks at the Flatiron Institute on Transport, Diffusions, and Sampling last year. Incl. Marilou Gabrié’s and Arnaud D ..read more

About 677,000 Gazaouis, are in “catastrophic” conditions today and a further 41% are in “emergency” conditions. Half of Gazaouis, i.e., 1.1 million people, will be in “catastrophe” or “famine” within weeks. Acute food insecurity puts all children under five at high risk of severe malnutrition and preventable death.  (IPC) Around 1.7 million people have been forced to flee their homes (UNRWA) Projections for the likely death toll in Gaza from all causes (incl. epidemics) over the months to August 2024 produce a range of 48,210 to 193,180 deaths, under a “status quo” scenario (The Guardian ..read more

On 24 April 2024, Guanyang Wang (Rutgers University, visiting ESSEC) will give a joint All about that Bayes – mostly Monte Carlo seminar on MCMC when you do not want to evaluate the target distribution In sampling tasks, it is common for target distributions to be known up to a normalizing constant. However, in many situations, evaluating even the unnormalized distribution can be costly or infeasible. This issue arises in scenarios such as sampling from the Bayesian posterior for large datasets and the ‘doubly intractable’ distributions. We provide a way to unify various MCMC algorithms, incl ..read more

..read more