**M**y nephew Paul and a fellow student made this nice mute video as a final project of his cinema degree in Rennes:

an attempt at bloggin, nothing more…

**M**y nephew Paul and a fellow student made this nice mute video as a final project of his cinema degree in Rennes:

ENSAE ParisTech and CREST are currently inviting applications for 3-year PhD scholarships in statistics (and economics, finance, and sociology). There is no constraint of nationality or curriculum, but the supervisor must be from ENSAE (Paris-Saclay) or ENSAI (Rennes-Bruz). The deadline is May 1, to be sent to Mrs Fanda Traore, at ensae.fr.

Applications should submitted (in French or in English), including :

– Curriculum vitae;

– Statement of research and teaching interests (10 pages);

– a cover letter

– the official transcripts of all higher education institutions from which you get a degree

– recommendation letters from professors, including a letter from the Ph.D. supervisor.

Selected candidates will be most likely interviewed at ENSAE‐CREST.

**I**n connection with the talk I gave last July in Rennes for MCqMC 2018, I posted yesterday a preprint on arXiv of the work that my [soon to defend!] Dauphine PhD student Changye Wu and I did on an alternative PDMP. In this novel avatar of the zig-zag sampler, a non-reversible, continuous-time MCMC sampler, that we called the Coordinate Sampler, based on a piecewise deterministic Markov process. In addition to establishing the theoretical validity of this new sampling algorithm, we show in the same line as Deligiannidis et al. (2018) that the Markov chain it induces exhibits geometrical ergodicity for distributions which tails decay at least as fast as an exponential distribution and at most as fast as a Gaussian distribution. A few numerical examples (a 2D banana shaped distribution à la Haario et al., 1999, strongly correlated high-dimensional normals, a log-Gaussian Cox process) highlight that our coordinate sampler is more efficient than the zig-zag sampler, in terms of effective sample size.Actually, we had sent this paper before the summer as a NIPS [2018] submission, but it did not make it through [the 4900 submissions this year and] the final review process, being eventually rated above the acceptance bar but not that above!

**I** made the “capital” mistake of walking across the entire NUS campus this morning, which is quite green and pretty, but which almost enjoys an additional dimension brought by such an intense humidity that one feels having to get around this humidity!, a feature I have managed to completely erase from my memory of my previous visit there. Anyway, nothing of any relevance. oNE talk in the morning was by Markus Eisenbach on tools used by physicists to speed up Monte Carlo methods, like the Wang-Landau flat histogram, towards computing the partition function, or the distribution of the energy levels, definitely addressing issues close to my interest, but somewhat beyond my reach for using a different language and stress, as often in physics. (I mean, as often in physics talks I attend.) An idea that came out clear to me was to bypass a (flat) histogram target and aim directly at a constant slope cdf for the energy levels. (But got scared away by the Fourier transforms!)

Lawrence Murray then discussed some features of the Birch probabilistic programming language he is currently developing, especially a fairly fascinating concept of delayed sampling, which connects with locally-optimal proposals and Rao Blackwellisation. Which I plan to get back to later [and hopefully sooner than later!].

In the afternoon, Maria de Iorio gave a talk about the construction of nonparametric priors that create dependence between a sequence of functions, a notion I had not thought of before, with an array of possibilities when using the stick breaking construction of Dirichlet processes.

And Christophe Andrieu gave a very smooth and helpful entry to partly deterministic Markov processes (PDMP) in preparation for talks he is giving next week for the continuation of the workshop at IMS. Starting with the guided random walk of Gustafson (1998), which extended a bit later into the non-reversible paper of Diaconis, Holmes, and Neal (2000). Although I had a vague idea of the contents of these papers, the role of the velocity **ν** became much clearer. And premonitory of the advances made by the more recent PDMP proposals. There is obviously a continuation with the equally pedagogical talk Christophe gave at MCqMC in Rennes two months [and half the globe] ago, but the focus being somewhat different, it really felt like a new talk [my short term memory may also play some role in this feeling!, as I now remember the discussion of Hilderbrand (2002) for non-reversible processes]. An introduction to the topic I would recommend to anyone interested in this new branch of Monte Carlo simulation! To be followed by the most recently arXived hypocoercivity paper by Christophe and co-authors.

**W**hile attending my last session at MCqMC 2018, in Rennes, before taking a train back to Paris, I was confronted by this radical opinion upon our previous work with Matt Moores (Warwick) and other coauthors from QUT, where the speaker, Maksym Byshkin from Lugano, defended a new approach for maximum likelihood estimation using novel MCMC methods. Based on the point fixe equation characterising maximum likelihood estimators for exponential families, when theoretical and empirical moments of the natural statistic are equal. Using a Markov chain with stationary distribution the said exponential family, the fixed point equation can be turned into a zero divergence equation, requiring simulation of pseudo-data from the model, which depends on the unknown parameter. Breaking this circular argument, the authors note that simulating pseudo-data that reproduce the observed value of the sufficient statistic is enough. Which is related with Geyer and Thomson (1992) famous paper about Monte Carlo maximum likelihood estimation. From there I was and remain lost as I cannot see why a derivative of the expected divergence with respect to the parameter θ can be computed when this divergence is found by Monte Carlo rather than exhaustive enumeration. And later used in a stochastic gradient move on the parameter θ… Especially when the null divergence is imposed on the parameter. In any case, the final slide shows an application to a large image and an Ising model, solving the problem (?) in 140 seconds and suggesting indecency, when our much slower approach is intended to produce a complete posterior simulation in this context.

%d bloggers like this: