## Archive for Cambodia

## Angkor beer

Posted in pictures, Travel, Wines with tags Angkor beer, beer, Cambodia, lager, Sianoukville, Siem Reap on July 20, 2019 by xi'an## La peste et la vigne [book review]

Posted in Books, Kids, Travel with tags book review, Cambodia, fantasy, French book, Joe Abercrombie, mercenary company, plague, Robin Hobb on March 17, 2019 by xi'an**D**uring my trip to Cambodia, I read the second volume of this fantasy cycle in French. Which I liked almost as much as the first volume since the author continues to explore the mystery of the central character Syffe and its relations with some magical forces at play in his universe. As in most stories uniquely centred on a single character point of view the recurring ponderings of Syffe about his role in life, the existence of supernatural forces, and his own sanity may tend to get annoying at time. But the escape from the mines and the subsequent stay in a mountain kingdom are well-paced, especially the description of the plague that allows such an escape. The last section is more connected with the first volume and sees more warfare, again with sudden reversals of fortune (no further spoiler!). The final chapters see a lot explained about many aspects of the story and the *raison d’être* of the character, even though the very last surprise is somewhat predictable. But opening new vistas for the future volumes. There are still many threads I could have pulled to point some potential influences of earlier cycles, from Stephen Donaldson’s Thomas Covenant chronicles, which I simply hated!, to Robin Hobb’s Soldier’s son. Since both stories convey the feeling of a magical force at the level of the whole land (or universe), with the unprepared and imperfect “hero” able to impact this land in dramatic ways. And again Elizabeth Moon’s Deeds of Paksenarion for the depiction of mercenary companies…

## optimal choice among MCMC kernels

Posted in Statistics with tags Angkor Wat, Cambodia, delayed acceptance, filamentary distribution, invariance, invariant measure, Markov kernel, Normandie, population Monte Carlo, Siem Reap, sparsity on March 14, 2019 by xi'an**L**ast week in Siem Reap, Florian Maire [who I discovered originates from a Norman town less than 10km from my hometown!] presented an arXived joint work with Pierre Vandekerkhove at the Data Science & Finance conference in Cambodia that considers the following problem: Given a large collection of MCMC kernels, how to pick the best one and how to define what best means. Going by mixtures is a default exploration of the collection, as shown in (Tierney) 1994 for instance since this improves on both kernels (esp. when each kernel is not irreducible on its own!). This paper considers a move to local weights in the mixture, weights that are not estimated from earlier simulations, contrary to what I first understood.

As made clearer in the paper the focus is on *filamentary* distributions that are concentrated nearby lower-dimension sets or manifolds Since then the components of the kernel collections can be restricted to directions of these manifolds… Including an interesting case of a 2-D highly peaked target where converging means mostly simulating in x¹ and covering the target means mostly simulating in x². Exhibiting a schizophrenic tension between the two goals. Weight locally dependent means correction by Metropolis step, with cost O(n). What of Rao-Blackwellisation of these mixture weights, from *weight x transition* to full mixture, as in our PMC paper? Unclear to me as well [during the talk] is the use in the mixture of basic Metropolis kernels, which are not absolutely continuous, because of the Dirac mass component. But this is clarified by Section 5 in the paper. A surprising result from the paper (Corollary 1) is that the use of *local* weights ω(i,x) that depend on the current value of the chain does jeopardize the stationary measure π(.) of the mixture chain. Which may be due to the fact that all components of the mixture are already π-invariant. Or that the index of the kernel constitutes an auxiliary (if ancillary) variate. (Algorithm 1 in the paper reminds me of delayed acceptance. Making me wonder if computing time should be accounted for.) A final question I briefly discussed with Florian is the extension to weights that are automatically constructed from the simulations and the target.

## Siem Reap conference

Posted in Kids, pictures, Travel, University life with tags Arkhangelsk, Bayes factors, Bayesian model choice, Bayesian model comparison, Cambodia, conference, CREST, Data Science and Finance conference, geometric ergodicity, group picture, Hyvärinen score, India, krama, Langevin MCMC algorithm, NGO, Pakistan, Sala Baï school, Siem Reap, Wasserstein distance on March 8, 2019 by xi'an**A**s I returned from the conference in Siem Reap. on a flight avoiding India and Pakistan and their [brittle and bristling!] boundary on the way back, instead flying far far north, near Arkhangelsk (but with nothing to show for it, as the flight back was fully in the dark), I reflected how enjoyable this conference had been, within a highly friendly atmosphere, meeting again with many old friends (some met prior to the creation of CREST) and new ones, a pleasure not hindered by the fabulous location near Angkor of course. (The above picture is the “last hour” group picture, missing a major part of the participants, already gone!)

Among the many talks, Stéphane Shao gave a great presentation on a paper [to appear in JASA] jointly written with Pierre Jacob, Jie Ding, and Vahid Tarokh on the Hyvärinen score and its use for Bayesian model choice, with a highly intuitive representation of this divergence function (which I first met in Padua when Phil Dawid gave a talk on this approach to Bayesian model comparison). Which is based on the use of a divergence function based on the squared error difference between the gradients of the true log-score and of the model log-score functions. Providing an alternative to the Bayes factor that can be shown to be consistent, even for some non-iid data, with some gains in the experiments represented by the above graph.

Arnak Dalalyan (CREST) presented a paper written with Lionel Riou-Durand on the convergence of non-Metropolised Langevin Monte Carlo methods, with a new discretization which leads to a substantial improvement of the upper bound on the sampling error rate measured in Wasserstein distance. Moving from p/ε to √p/√ε in the requested number of steps when p is the dimension and ε the target precision, for smooth and strongly log-concave targets.

This post gives me the opportunity to advertise for the NGO Sala Baï hostelry school, which the whole conference visited for lunch and which trains youths from underprivileged backgrounds towards jobs in hostelery, supported by donations, companies (like Krama Krama), or visiting the Sala Baï restaurant and/or hotel while in Siem Reap.