a journal of the plague year [confined reviews]

Watched TV series His Dark Materials produced for the BBC, which is much much better than the earlier film, as the actors are all fabulous—first and foremost Lyra, but also Ma Costa, the Gyptian Muter Courage—, the gypsy community is given a much stronger role, the characters are deep and complex, as eg Mrs and Mr Coulter, both ready to sacrifice kids for the greater “good” without appearing as absolute monsters! The special effects are a wee bit deficient as often with BBC productions but not enough to make a case. Although I sort of cringed each time a bear moved!

Read The Voyage of the Jerle Shannara trilogy by Terry Brooks, which I noticed standing on my son’s bookshelves. The original Shannara Trilogy was one of the very first fantasy books I read in English in my undergrad years (after Lord of the Rings of course and possibly The Chronicles of Thomas Covenant), which did not leave me with an everlasting feeling of superlative literature, to say the least. This avatar of the original Sword of Shannara trilogy did nothing to improve my feelings as the plot is lazy at best, with super-powered villains suddenly acting, last second deus ex machina rescues, endless internal debates, heavy hints at treacheries and double-treacheries, and, worst of all!, intrusion of 20th century technology, e.g., computers, AIs and robots, that the far future characters make sense of. Only suitable for a time of lockdown and even then… I should have left it on the bookshelf! Incidentally, one fight scene against a cyborg was highly reminiscent of the black knight scene in Holy Grail!

Watched by chance Tarantino’s Reservoir Dogs. For the first time. And was totally un-impressed. Highly pretentious construction falling flat from being a modern reconstruction of antique dramas, endless dialogues (which could have been cut by half if removing all the occurrences of fucking from them), boring and threadbare story, and artificial characters that essentially make no sense. I cannot fathom why this film is so highly ranked..! (And even less to witness it being compared with Rashomon!)

Read [part] of Jin Yong’s Legends of the Condor Heroes (射鵰英雄傳) but, lockdown or not, I simply could not finish it. Despite its fantasy approach to Chinese martial arts, which I usually enjoy (at least in planes!), and some proximity with the Judge Dee stories by van Gulik, the story felt very contrived and somewhat out of reach, plus [not yet] Genghis Khan being depicted in a fairly positive way [at least in the part I read]. Too irrealist for my reading buds, I presume…

Cooked plenty of new dishes, thanks to the delivery of weekly farmer boxes, from radish stems & buckwheat pancakes to celery roots purées, to fregola sarda (leftovers from ISBA 2016!) con acciughe, to chard gratins, to pea pod and cauliflower core soups, to flaxseed bread and buckwheat naans (as we ran out of wheat flour). We also managed to use and survive most of the out-of-date cans and bags that had stood forgotten in the back of our cupboard… Not visiting a supermarket for two months was actually most pleasant, living very nicely from the above mentioned farmer boxes and the occasional delivery from a cheesemonger, and supplementing weekly visits to the baker with attempts at home made bread.

Read Matha Well’s Murderbot diaries, my first read on a Kindle!, for free courtesy of Tor. Starting with All Systems Red, which won the 2017 Nebula Award for Best Novella, the 2018 Hugo Award for Best Novella, the 2018 Locus Award, and the American Library Association‘s Alex Award. Very good if somewhat classical (Blade Runner anyone?!) trope of the rogue robot turned autonomous and human, so human! This is a sequence of novellas which means a fast-paced story and an efficient style. (Including a less exciting third novella, due to a lazy scenario.) More mind-candy à la John Scalzi than profound literature but quite enjoyable for a quick read during lunch or tea break! But which induced me to buy the first and incoming novel in the series,  Network Effect. (To be commented in a subsequent entry…)

Leading to (re)read the Interdependency trilogy by John Scalzi, the last volume in the series being just out. Very lazy buildup, in the traditional spirit of a few people driving the future of the entire Universe, with unlimited resources and unrestricted hacking abilities, but with funny dialogues, as usual with Scalzi. In this binge (re)read, I actually realised the frustrating intricacies of Kindle ordering as (i) I could not use my amazon.com account and hence none of my associate gains (ii) I could not merge several amazon.fr accounts and (iii) prices varied a lot between using directly the Kindle and ordering from amazon.fr…

And even growing some salads and radishes over the two months and eating them before the end of the lockdown, as the weather in Paris was quite mild most of the time. Although it meant a daily-basis fight with slugs. The arugula did not resist that well, though…

Reading Tade Thompson’s Rosewater for more than a month, having trouble keeping my concentration as the story goes in loops and not a particularly well settled plot. With a central idea of an alien race taking over humanity a few cells at a time. Which reminded me of Greg Bear’s Blood Music I read during the first year of my PhD. The book has some appeal, from being located in Nigeria 30 years from now to America having completely vanished from the map after Trump pulled the ultimate drawbridge. It won the 2019 Arthur Clarke Award after all! But I found it too hard to complete to even consider embarking upon the next two volumes on the trilogy…

Monica di Sardegna [Perdera]

Au’Bayes 17

Some notes scribbled during the O’Bayes 17 conference in Austin, not reflecting on the highly diverse range of talks. And many new faces and topics, meaning O’Bayes is alive and evolving. With all possible objectivity, a fantastic conference! (Not even mentioning the bars where Peter Müller hosted the poster sessions, a feat I would have loved to see duplicated for the posters of ISBA 2018… Or the Ethiopian restaurant just around the corner with the right amount of fierce spices!)

The wiki on objective, reference, vague, neutral [or whichever label one favours] priors that was suggested at the previous O’Bayes meeting in Valencià, was introduced as Wikiprevia by Gonzalo Garcia-Donato. It aims at classifying recommended priors in most of the classical models, along with discussion panels, and it should soon get an official launch, when contributors will be welcome to include articles in a wiki principle. I wish the best to this venture which, I hope, will induce O’Bayesians to contribute actively.

In a brilliant talk that quickly reverted my jetlag doziness, Peter Grünwald returned to the topic he presented last year in Sardinia, namely safe Bayes or powered-down likelihoods to handle some degree of misspecification, with a further twist of introducing an impossible value `o’ that captures missing mass (to be called Peter’s demon?!), which absolute necessity I did not perceive. Food for thoughts, definitely. (But I feel that the only safe Bayes is the dead Bayes, as protecting against all kinds of mispecifications means no action is possible.)

I also appreciated Cristiano Villa’s approach to constructing prior weights in model comparison from a principled and decision-theoretic perspective even though I felt that the notion of ranking parameter importance required too much input to be practically feasible. (Unless I missed that point.)

Laura Ventura gave her talk on using for ABC various scores or estimating equations as summary statistics, rather than the corresponding M-estimators, which offers the appealing feature of reducing computation while being asymptotically equivalent. (A feature we also exploited for the regular score function in our ABC paper with Gael, David, Brendan, and Wonapree.) She mentioned the Hyvärinen score [of which I first heard in Padova!] as a way to bypass issues related to doubly intractable likelihoods. Which is a most interesting proposal that bypasses (ABC) simulations from such complex targets by exploiting a pseudo-posterior.

Veronika Rockova presented a recent work on concentration rates for regression tree methods that produce a rigorous analysis of these methods. Showing that the spike & slab priors plus BART [equals spike & tree] achieve sparsity and optimal concentration. In an oracle sense. With a side entry on assembling partition trees towards creating a new form of BART. Which made me wonder whether or not this was also applicable to random forests. Although they are not exactly Bayes. Demanding work in terms of the theory behind but with impressive consequences!

Just before I left O’Bayes 17 for Houston airport, Nick Polson, along with Peter McCullach, proposed an intriguing notion of sparse Bayes factors, which corresponds to the limit of a Bayes factor when the prior probability υ of the null goes to zero. When the limiting prior is replaced with an exceedance measure that can be normalised into a distribution, but does it make the limit a special prior? Linking  υ with the prior under the null is not an issue (this was the basis of my 1992 Lindley paradox paper) but the sequence of priors indexed by υ need be chosen. And reading from the paper at Houston airport, I could not spot a construction principle that would lead to a reference prior of sorts. One thing that Nick mentioned during his talk was that we observed directly realisations of the data marginal, but this is generally not the case as the observations are associated with a given value of the parameter, not one for each observation.The next edition of the O’Bayes conference will be in… Warwick on June 29-July 2, as I volunteered to organise this edition (16 years after O’Bayes 03 in Aussois!) just after the BNP meeting in Oxford on June 23-28, hopefully creating the environment for fruitful interactions between both communities! (And jumping from Au’Bayes to Wa’Bayes.)

Chateau Mussar

ISBA 2016 [#7]

This series of posts is most probably getting by now an imposition on the ‘Og readership, which either attended ISBA 2016 and does (do?) not need my impressions or did not attend and hence does (do?) not need vague impressions about talks they (it?) did not see, but indulge me in reminiscing about this last ISBA meeting (or more reasonably ignore this post altogether). Now that I am back home (with most of my Sard wine bottles intact!, and a good array of Sard cheeses).

This meeting seems to be the largest ISBA meeting ever, with hundreds of young statisticians taking part in it (despite my early misgivings about the deterrent represented by the overall cost of attending the meeting. I presume holding the meeting in Europe made it easier and cheaper for most Europeans to attend (and hopefully the same will happen in Edinburgh in 2018!), as was the (somewhat unsuspected) wide availability of rental alternatives in the close vicinity of the conference resort. I also presume the same travel opportunities would not have been true in Banff, although local costs would have been lower. It was fantastic to see so many new researchers interested in Bayesian statistics and to meet some of them. And to have more sessions run by the j-Bayes section of ISBA (although I found it counterproductive that such sessions do not focus on a thematically coherent theme). As a result, the meeting was more intense than ever and I found it truly exhausting, despite skipping most poster sessions. Maybe also because I did not skip a single session thanks to the availability of an interesting theme for each block in the schedule. (And because I attended more [great] Sard dinners than I originally intended.) Having five sessions in parallel indeed means there is a fabulous offer of themes for every taste. It also means there are inevitably conflicts when picking one’s session.

Back to poster sessions, I feel I missed an essential part of the meeting, which made ISBA meetings so unique, but it also seems to me the organisation of those sessions should be reconsidered against the rise in attendance. (And my growing inability to stay up late!) One solution suggested by my recent AISTATS experience is to select posters towards lowering the number of posters in the four poster sessions. The success rate for the Cadiz meeting was 35%.) The obvious downsizes are the selection process (but this was done quite efficiently for AISTATS) and the potential reduction in the number of participants. A medium ground could see a smaller fraction of posters to be selected by this process (and published one way or another as in machine-learning conferences) and presented during the evening poster sessions, with other posters being given during the coffee breaks [which certainly does not help in reducing the intensity of the schedule]. Another and altogether solution is to extend the parallelism of oral sessions to poster sessions, by regrouping them into five or six themes or keywords chosen by the presenters and having those presented in different rooms to split the attendance down to human level and tolerable decibels. Nothing preventing participants to visit several rooms in a given evening. Or to keep posters for several nights in a row if the number of rooms allows.

It may also be that this edition of ISBA 2016 sees the end of the resort-style meeting in the spirit of the early Valencia meetings. Edinburgh 2018 will certainly be an open-space conference in that meals and lodgings will be “on” the participants who may choose where and how much. I have heard many times the argument that conferences held in single hotels or resorts facilitated the contacts between young and senior researchers, but I fear this is not sustainable against the growth of the audience. Holding the meeting in a reasonably close and compact location, as a University building, should allow for a sufficient degree of interaction, as was the case at ISBA 2016. (Kerrie Mengersen also suggested that a few restaurants nearby could be designated as “favourites” for participants to interact at dinner time.) Another suggestion to reinforce networking and interacting would be to hold more satellite workshops before the main conference. It seems there could be a young Bayesian workshop in England the prior week as well as a summer short course on simulation methods.

Organising meetings is getting increasingly complex and provides few rewards at the academic level, so I am grateful to the organisers of ISBA 2016 to have agreed to carry the burden this year. And to the scientific committee for setting the quality bar that high. (A special thought too for my friend Walter Racugno who had the ultimate bad luck of having an accident the very week of the meeting he had contributed to organise!)

[Even though I predict this is my last post on ISBA 2016 I would be delighted to have guest posts on others’ impressions on the meeting. Feel free to send me entries!]