
Archive for Japan
hotaruraito
Posted in Statistics with tags bambou forest, fireflies, Japan, Kei Nomiyama, Open Photographer of the Year 2020, Shikoku, The Guardian, wildlife photography on November 17, 2020 by xi'an
a journal of the plague year [latter August reviews]
Posted in Books, Kids, Mountains, pictures, Travel with tags amazon associates, Ann Leckie, book reviews, Briançon, Daniel Defoe, film review, films, French Alps, gender inequality, Gruyère, Hamlet, homecooking, homegrown vegetables, Japan, Journal of the Plague Year, MIchelin starred restaurant, Natsuo Kirino, NYT, risotto, squash vine, tarte aux noix, Université Paris Dauphine on October 10, 2020 by xi'anRead during the first week of our Alpine vacations a Japanese gore novel by Natsuo Kirino, Out, which I found in the book exchange zone at Dauphine earlier in July. The book is more impressive for a social criticism of the condition of working class women the Japanese society than for its psychological thriller nature, even though the later is well-enough conducted to induce a page-turning commitment… The four women at the centre of the story are drawn in fine and convincing details and the practical cynicism of most of them makes the novel avoid the easy and rosy idealisation of a crime sisterhood. The slow unraveling of the past of these women exhibits how they ended up in a food-packaging night-shift job by virtue (!) of a gender inequality inherent to the social structure. The book is not 100% perfect, especially in the final moments, even though the surprising readiness of Masako to turn herself (almost) into a victim is much more subtle than it sounds (spoiler!). Still a major novel, if one can manage to stand the gory details..!
Had another chance great meal in a Michelin-recommended restaurant in Briançon, Au Plaisir Ambré, with a surprising sea-food theme including Granville whelks tartare, lobster samosas and grayling en croûte (except the crust was not salt but brioche!), the later with the distinctive taste of river fish. The more pleasant as an earlier experience at a Michelin-starred restaurant in Paris was not so exciting, with a risotto smothered by Gruyère!, a culinary lèse-majesty! Also tasted wonderful tartes aux noix made by the housekeeper of one of our vacation rentals. Rich enough for a whole day of hiking.
Read the Raven Tower by Ann Leckie, of which I expected much and which I alas found quite poor (compared with the fabulous Ancillary series). Maybe because I found too many connections with the stunning Ka, which takes the raven’s perspective on human history. Maybe because the Raven is the bad guy/god in this story. Even taking the story as a theatre play (as it builds on Hamlet) did not really work for me. The few characters are not sufficiently deep, the interaction between gods and humans is rather simplistic (although the world-building shows promises) and the conclusion is botched in my opinion. The style is original and the book well-written, however. Plus the book is short and single-volumed! (But I do not get the rave reviews!)
in the name of eugenics [book review]
Posted in Statistics with tags Annals of Eugenics, Biometrika, book review, eugenics, Japan, John Burdon Sanderson Haldane, Lionel Penrose, Muller, Nazi State, Ronald Fisher, Soviet Union, The New Yorker, Trofim Lysenko on August 30, 2020 by xi'anIn preparation for the JSM round table on eugenics and statistics, organised by the COPSS Award Committee, I read the 1985 book of Daniel Kevles, In the Name of Eugenics: Genetics and the Uses of Human Heredity, as recommended by Stephen Stiegler. While a large part of the book was published in The New Yorker, in which Kevles published on a regular basis, and while he abstains from advanced methodological descriptions, focussing more on the actors of this first attempt at human genetics and of the societal consequences of biased interpretations and mistaken theories, his book is a scholarly accomplishment, with a massive section of notes and numerous references. This is a comparative history of eugenics from the earliest (Francis Galton, 1865) to the current days (1984) since “modern eugenics” survived the exposure of the Nazi crimes (including imposed sterilizations that are still enforced to this day). Comparative between the UK and the US, however, hardly considering other countries, except for a few connections with Germany and the Soviet Union, albeit in the sole perspective of Muller’s sojourn there and the uneasy “open-minded” approach to Lysenkoism by Haldane. (Japan is also mentioned in connection with Neel’s study of the genetic impact of the atomic bombs.) While discussing the broader picture, the book mostly concentrates on the scientific aspects, on how the misguided attempts to reduce intelligence to IQ tests or to a single gene, and to improve humanity (or some of its subgroups) by State imposed policies perceived as crude genetic engineering simultaneously led to modern genetics and a refutation of eugenic perspectives by most if not all. There is very little about statistical methodology per, beside stories on the creation of Biometrika and the Annals of Eugenics, but much more on the accumulation of data by eugenic societies and the exploitation of this data for ideological purposes. Galton and Pearson get the lion’s share of the book, while Fisher does not get more coverage than Haldane or Penrose. Overall, I found the book immensely informative as exposing the diversity of scientific and pseudo-scientific viewpoints within eugenism and its evolution towards human genetics as a scientific endeavour.
non-reversible guided Metropolis–Hastings
Posted in Mountains, pictures, Statistics, Travel with tags arXiv, compacity, group action, Haar measure, Hamiltonian Monte Carlo, Japan, Kii peninsula, Markov chain, Metropolis-Hastings algorithm, Mount Koya, non-reversible diffusion, non-reversible MCMC, Osaka on June 4, 2020 by xi'anKengo Kamatani and Xiaolin Song, whom I visited in Osaka last summer in what seems like another reality!, just arXived another paper on a non-reversible Metropolis version. That exploits a group action and the associated Haar measure.
Following a proposal of Gustafson (1998), a ∆-guided Metropolis–Hastings kernel is based on a statistic ∆ that is totally ordered and determine the acceptance of a proposed value y~Q(x,.) by adding a direction (-,+) to the state space and moving from x if ∆x≤∆y in the positive direction and if ∆y≤∆x in the negative direction [with the standard Metropolis–Hastings acceptance probability]. The sign of the direction switches in case of a rejection. And the statistic ∆ is such that the proposal kernel Q(x,.) is unbiased, i.e., agnostic to the sign, i.e., it gives the same probability to ∆x≤∆y and ∆y≤∆x. This modification reduces the asymptotic variance compared with the original Metropolis–Hastings kernel.
To construct a random walk proposal that is unbiased, the authors assume that the ∆ transform takes values in a topological group, G, with Q further being invariant under the group actions. This can be constructed from a standard proposal by averaging the transforms of Q under all elements of the group over the associated right Haar measure. (Which I thought implied that the group is compact, except I forgot to account for the data update into a posterior..!) The worked-out example is based on a multivariate autoregressive kernel with ∆x being a rescaled non-central chi-squared variate. In dimension 24. The results show a clear improvement in effective sample size per second evaluation over off-the-shelf random walk and Hamiltonian Monte Carlo versions.
Seeing the Haar measure appearing in the setting of Markov chain Monte Carlo is fun!, as my last brush with it was not algorithmic. I would think the proposal only applies to settings where the components of the simulated vector are somewhat homogeneous in that the determinationthe determination of both the group action and a guiding statistic seem harder in cases where these components take different meaning (or live in a weird topology). I also lazily wonder if selecting the guiding statistic as a gradient of the log-target would have any interest.