Archive for the Running Category

ISBA⁴

Posted in Books, pictures, Running, Statistics, Travel, University life with tags , , , , , , , , , , , , , , , , on July 3, 2026 by xi'an

After a 5am run in emptied and very humid Nagano, to tour the castle grounds, if not the castle itself, with a rather unpleasant urban route, and a recovery matcha scone at the local French (-inspired) bakery, resisting the kouign aman!, I attended the highly diverse Bayesian non-parametric session (with mentions of Lisieux, near my childhood grounds, if in relation with English history, since the bishop of Lisieux appeared in Geoff Nicholls’ graph analysis. And Gregor Katzner’s repulsive mixtures.)

Then skipped Peter Muller’s de Finetti talk [sorry Peter!] with a few friends to get to nearby Atsuta-jingū (Shinto shrine) and the nearby Bunka-den, with a famous hitsumabushi (eel) restaurant that was alas fully booked. But a slightly less fancy one delivered well enough. This was a nice place, with a large park, full of worshippers clapping and touring the shrines. We even X’ed a group of salarymen in their company uniform welcomed by a Shinto priest.

And I was back in time for the junior Bayesian (jISBA) session. With Deborah Sulem talking on statistical fairness, which I could not fully distinguish from the general issue of missing covariates (corresponding to discriminated categories) or from unbalanced sampling. Jack Jewson (also coauthor of the paper with Deborah) argued about using quasi-likelihoods for consistent model selection, presumably most convincingly but jetlag hit during his talk and I had a fit of micro-naps… And Noirrit Chandra discussed a privacy-preserving Bayesian nonparametric approach through clusters and the release of MCMC outputs, close enough to my own research to fight the naps. The day closed with Emtiyaz Khan talking as at BayesComp last year on acceleration techniques as sustainable AI (although I am afraid this does not tackle the unsustainability of AI as a whole).

ISBA³

Posted in pictures, Running, Statistics, Travel, University life with tags , , , , , , , , , , , , , , , , , , , , , , , on July 2, 2026 by xi'an

After another absurdly early run along the Sendai River, in higher humidity than yesterday, I had plenty of time to have breakfast and commute to the conference centre for our privacy section. (“Ours” since I organised and chaired the session, but also all speakers were related with our ERC OCEAN project.) With talks by Antoine Luciano (Dauphine), Shenggang Hu (Warwick) and Joshua Bon (formerly Dauphine), Shenggang presenting his work with Gareth on calibrating a DP, noisy, unbiased, version of Metropolis-Hastings. Given the other sessions highly competing with ours, this 100% OCEAN session was well-attended! My second morning session was the theory & method part of the Savage Award, with unfortunately two of the speakers stuck in the US for visa issues and presenting remotely. There have been years where this session suffered from competition from parallel sessions, but this time showed a quite decent attendance.

As most members of the scientific committee of the BayesComp mirror in Aussois were present, we went out for lunch at a nearby hitsumabushi restaurant to plan registrations and local sessions. Which proved very productive despite enjoying the fantastic eel dishes! If making me miss the beginning of the afternoon session… and then the whole session as the room on predictive Bayes was packed (and some speakers had already delivered on the Isle of Skye). I managed to get to Bottond Szabo’s Foundation lecture, with again common threads with Skye, and then returned to my rental as I was quickly crashing…

ISBA 2026²

Posted in Books, pictures, Running, Statistics, Travel, University life with tags , , , , , , , , , , , , , on July 1, 2026 by xi'an

One morning session on optimal transport after first-hand witnessing the impressive ballet of orderly lines entering the subway at Nagoya Station (and a very early run along the river and a high humidity rate, hence the picture of empty street at 5am). With Hugo Lavenant exhibiting optimal rates for Bayesian nonparametrics using Wasserstein distances, Pierre Jacob coupling MCMC chains, and Anya Katsevich investigating non-Gaussian asymptotic distributions in high dimensions (beyond Bernstein-von Mises). Then I tried to attend the session on Bayesian Uncertainty Quantification and Posterior Sampling for Large-Scale Generative Models, but it proved too popular for the number of seats, and I ended up discussing with others. After a nap related to my jetlag induced, early, rise I went back to chair Sid Chib’s Foundation Lecture, where he discussed the use of an orbit of models in Bayesian model choice, rather than the (MAP) most likely one. Based on their 2018 JASA paper which I already discussed in Paris with Anna Simoni presenting. Hence reminding me of points I presumably already made, from the issue of having too many models to realistically explore to constructing coherent priors across them, with the fractional, empirical, proxy of using a (same) fraction of the sample as a learning sample, to more philosophical issues like missing a utility function about having to chose a model, especially with all models being wrong, missing an uncertainty quantification on the evidence itself, rather than using most likely models (MAP!), called an orbit by Sid (which requires some calibration). Since the uncertainty represented by the sample induces an uncertainty in the ranking of models. And a most appropriate, almost local, occurrence of the Rashomon principle!!! And I finished the day mixing with many friends in the poster session¹, where Darren Wraith presented our ongoing work on novel, adaptive, importance, sampling.

Pegasus half-marathon meltdown [01:30:07 – 245/5176 – 2/59 M6M]

Posted in pictures, Running, Travel with tags , , , , , , , , , , , , , , , , , on June 9, 2026 by xi'an

Huge disappointment with this favourite race of mine! It is unclear what caused my underperforming this time, since I had trained regularly for two months, with many long distance runs and several intensity ones, weekly. The temperature was mild, the constant wind none too strong, but I slowed down almost from the beginning… And could not keep up with the 1h30 pacers when they passed me 5km before the finish line (even though they were running faster than the 1h30 target!). Lack of rest the final week? A fast 12km bike ride to the Saint-Lazare train station the previous day (in order to avoid the nightmare of getting back to Caen train station on race day)? Too much weight loss the last two weeks? Too long a warm-up run the same morning? Need of gels mid-race? The most frustrating is that I would have ended first in the previous category (M5M).

a journal of the Hugo year

Posted in Books, Kids, Mountains, pictures, Running, Travel, University life, Wines with tags , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , on June 3, 2026 by xi'an

Read (over the past months) books I forgot to record in the Journal series namely, The Practice, the Horizon, and the Chain, by Sofia Samatar, a rather terrible take on Wells’ Time Machine where exploited live in the darkest parts of a space-ship and upper classes in the nicest places. With an unconvincing trio of characters and a paper-thin scenario, including an unconvincing pastiche of academic pettiness. Quite the disappointment! The latest Ben Aaronovitch’s Rivers of London novel, Stone & Sky, a rather nice instalment in the series, if only because it is set in Northern Scotland (where I read it!), but with some weaknesses in the plot and a puzzling two-voice narrative that sounds unbalanced (in favour of Peter vs. Abigail). Plus a wee bit caricaturing Scottish people, methinks! And then, being a Hugo voting member for 2026, several books and short stories that I receive as part of the LACon package, like The Raven Scholar by Antonia Hodgson read first because I love ravens! Especially the fantastic Ka: Dar Oakley in the Ruin of Ymr. I had trouble beginning the book, but once the setting was established, I could follow the main character more easily. The character is enticing but the universe building is shaky and the scenario weak on many planes, making the central issues of solving a murder and finding a new emperor/ress more of a summer camp challenge than crucial problems. Plus an all-too-common fixation on meals and drinks consumed by the characters… It is getting worse towards the end. Likely my (first and) last volume in the Eternal Path Trilogy! Not high in my Hugo ranking then. And the (Murderbot) novelette “Rapport: Friendship, Solidarity, Communion, Empathy” by Martha Wells. Frankly disappointing. I do love the Murderbot series, but this short story highly disappointed me. Between feelings of déjà vu and annoyance at the constant bickering between the characters that reminded me of the nadir of the relationship between my two kids! Absolutely worth ignoring! Even in the Hugo ranking.

Due to repeated travel, plus a heat wave, I did not cook much besides salads and fruit purées, but enjoyed a haggis pie on Skye. And two (local versions of) pissaladières in Marseille. I also had to transfer my olives of the (2025) year into new jars as some had started to grow mould. Fortunately. most of them remained edible if somewhat sour. Thanks to Omiros’ expert advice, they are now maturing in olive oil.

Watched Sins of Kujo, inspired from a popular manga series, which is quite puzzling for its moral and ethical ambiguities.