I first got attracted by this book thanks to its beautiful cover (in a Seattle bookstore last year)! The book is an aggregate of three stories, loosely related around the themes of altruism and disastrous good intentions. I did not like the first story, about the disintegration of a gay couple by ways of (OCD) psychiatric issues as well as an increasing radicalism towards Ayush’s societal choices, with some shocking episodes as when he shows illegal filming from pig abattoirs to their young children. I saw some worth in the second story, when a classic academic gets obsessed with the migration of a Sudanese child-soldier to the point of obsession, removing herself from her job and civic duties, as in not reporting a possible hit & run, and eventually gifting a kidney to the refugee’s brother. As a dubious reparation for her grand-parents’ involvement in the British Raj colonialism. I mostly enjoyed the third one, where Sabita, a rural Bengali or Bangladeshi woman, receives a cow from experimental economists (in the spirit of Esther Duflo’s school), a stupendous gift that is slowly unraveling her family and her precarious finances. However, my overall impression is one of an overly ideological posture, tending to caricatures (esp. of academics) and compartmentalisation of individuals, to the detriment of the book per se and to the depth of its characters. The last story is further strongly condescending towards the main character who proves unable to manage the cow (and her family), again forcing the trait for the sake of the political argument. The Guardian is more appreciative of the book, however.
Archive for appam
a journal of the chaos (and rhubarb) year
Posted in Books, Kids, Mountains, pictures, Travel, Wines with tags Air France, alien intelligence, appam, Black Plague, book reviews, buckwheat, Chamonix, Chennai, COVID-19, cuisine, Daniel Defoe, domestic violence, E.M. Forster, fantasy, gardening, gun violence, homegrown, India, Japan, Journal of the Plague Year, Lysefjord, Norway, Paris, Russian invasion, south Indian cuisine, Tamil Nadu, Thirty-six Views of Mount Fuji, Ukraine, whey on July 30, 2025 by xi'an Read Fjellet, geværet, vannet (A mountain, a gun, a lake) by Lars Ramslie (in French, published by the Chamonix based Paulsen editions). A perturbing recollection of a broken childhood between the Norwegian outdoors and violent parenting, in the shadow of an out-of-control father. To the point I found it rather hard to finish the book, the author (and son) being often borderline apologetic for his father’s violent outbursts. That he survived such a trauma is astounding. That local social services could not keep his father away is a shame… I also read E.M. Forster’s A Passage to India classic, while travelling to Chennai, which already reviewed in a separate post.
Beyond indulging in South Indian dishes and a never ending range of appams and local fruits, I made rhubarb preserve from a home-grown rhubarb planting, sometime supplemented with the first figs from our fig-tree and sometime augmented by farmer market sticks. Picked too hot a day to make a ceviche, despite a quick dip in lemon as I returned from the market. (No aftereffect, it just did not taste nice.) And panned an experimental monkfish liver that proved nice and ejnoyable (and with a very mild taste compared with the veal liver I had to eat once a week as a child).

BayesComp 2025.2
Posted in Kids, pictures, Statistics, Travel, University life with tags appam, Arianna Rosenbluth, BayesComp 2025, Bayesian neural networks, Bayesian robustness, Bayesian semi-parametrics, characteristic function, chili pepper, Chinatown, cut models, durian, equator, exam, Gaussian processes, Gibbs measure, Gibbs posterior, Hamiltonian Monte Carlo, Harvard University, HMC, MASH, Maxwell Hawker market, National University Singapore, NUS, PDMP, Poisson equation, popiah, pseudo-marginal MCMC, rojak, safe Bayes, self-normalised importance sampling, Shanghai, Singapore, stereographic MCMC, stochastic gradient MCMC, street food, unbiased MCMC, Université Paris Dauphine, xiaolongbao, zigzag algorithm on June 19, 2025 by xi'an
The main BayesComp²⁵ conference started with Pierre Jacob’s plenary talk on his recent advances on coupling for unbiased MCMC—currently ERC grantee on that topic—. Raising lazy questions like using a different target or transition kernel for the second chain in the coupling, connecting the Poisson equation and control variates, handling the signed issue with the unbiased approximations. Interestingly, they obtain an unbiased estimator of the asymptotic variance of the unbiased estimator. And a correction for self-normalised importance sampling, which has some connections with our 1996 (?) pinball sampler. Also an evaluation of the median of means, rather than the average of means, which is a thing I had been (lazily) contemplating for a while (On the greedy side, as I was writing my recovery exam for my Monte Carlo course, I realised the results Pierre presented could be somewhat recycled into exam problems!)
My first parallel session was on gradient-based methods with a talk by Francesca Crucinio on proximal particle Langevin algorithms (similar to the one she gave in PariSanté last year), a talk by Zhihao Wang on stereographic multiple try Metropolis(-Rosenbluth-Teller) that unsurprisingly recovers ergodicity thanks to the compactness of the ball. For which I wonder why a Normal proposal makes complete sense since one could consider a mover after the projection instead and why iid rather than repelling multiple proposals are used… The last speaker was just out from the plane from California, Siddharth Vishwanath who spoke about repelling-attracting HMC. With very nice animations of HMC, if reaching the main point of using both negative and positive frictions a few minutes before the session finished. The method preserves volume and potential, if not energy.
Speaking of which (energy), I find myself struggling with my less than 6 hours of sleep since arrival during the first afternoon session, despite a fiery hot spot lunch, which means in plainer terms that I alas dozed in and out of the talks. The second session saw Jack Jewson exposing in deeper details the exact PDMP algorithm for Gibbs measures Jeremias Knoblauch mentioned yesterday. And Jonathan Huggins as well, using Gaussian processes as proxies for expected likelihoods, with lower guarantees than pseudo-marginal versions. In a mildly connected way, Robin Ryder went through the resolution of the ecological inference challenge they produce with Nicolas Chopin and Théo Valdoire (all authors with whom I am connected, Théo being a brillant student of our MASH Master last year and now in Harvard, hopefully till the end of his PhD!)


On the extra-academic curriculum, I had a yummy dinner in the Maxwell Hawker (street) food centre, incl. Xiao Long Bao that cooled down fast enough to avoid the usual scalding effect, plus rojak a mixed fruit and vegetable fried in a peanut sauce that I had never tasted before, popiah (ditto), chili noodles, and an appam with durian deepfried balls as a fabulous and unexpected dessert.
A passage to India & to 2025
Posted in Kids, pictures, Running, Travel with tags A Passage to India, air pollution, appam, Bengaluru, Calcutta, CDG, chaat, challa, ChatGPT, cocoa, Delhi, dosa, e-visa, E.M. Forster, elephants, Ernakulam district, ferry, Finger Lakes, fog, idli, IISA, IISA 2024, Iran, Iraq, Israel, Ithaca, Kerala, Kumarakom, Malayalam, masala chai, momo, Munnar, Munnar tea, New Year's Eve, paratha, pepper, Saravana Bhavan, Sinaï, spices, Sri Lanka frogmouth bird, Syria, tea, Ukraine invasion, University of Calcutta, Vembanad Lake, Western Ghats on January 16, 2025 by xi'anAnother great trip to India in association with the bi-yearly Winter IISA (International Indian Statistical Association) conference, including the opportunity to visit Kerala since the conference was taking place in Kochi (formerly Cochin). And a relatively smooth and relaxing trip as well! (And involuntarily repeating the Forsterite title of the earlier post.)
We left (as earlier) Paris on Xmath day, with de Gaulle airport busier than expected, including by the staff there, since a shortage of both border police officers and of luggage handlers caused a one-hour delay, with a full airplane to Bengaluru. Our flight took a rather circuitous route to avoid less secure air spaces, namely Ukraine, Israël, Syria, Iraq, and Iran, but also staying away from Houtis, hence turning sharply over the Sinaï to fly over Saudi Arabia. Massala chai onboard! My next seat neighbours sounded busy rescheduling their vacations (or others’?) to a visa-free country as some members of their party had apparently been denied boarding for that reason. (And I indeed had to frantically search through emails to recover the confirmation message from the Indian e-visa service provider at the boarding gate. But I had a great time reviewing grant proposals for most the flight!)


The last station was Kuramakom, on the shores of the huge Vembanad Lake—longer than the Finger lakes surrounding Ithaca, New York—, where we saw plenty of birds as we were ferried through the backwaters at dusk. Visited the local bird sanctuary, at dawn to optimize our chances, but they remained low enough to only see a … tortoise crossing the path and a large fruit bat flying away. Day temperatures were such as making reading in the shade almost compulsory, which helped cleaning the pile of books I had taken with me.




