Archive for Markov chain Monte Carlo

approximate Bayesian inference [survey]

Posted in Statistics with tags , , , , , , , , , , , , , , , , , , on May 3, 2021 by xi'an

In connection with the special issue of Entropy I mentioned a while ago, Pierre Alquier (formerly of CREST) has written an introduction to the topic of approximate Bayesian inference that is worth advertising (and freely-available as well). Its reference list is particularly relevant. (The deadline for submissions is 21 June,)

away from CIRM

Posted in Mountains, pictures, Running, Statistics, Travel, University life with tags , , , , , , , , , on November 5, 2020 by xi'an

Due to the new lockdown measures enforced in France and in particular in Marseilles, the CIRM workshop on QMC and randomness has turned virtual, and I will thus give my talk on Coordinate sampler : A non-reversible Gibbs-like sampler from Paris. Rather than from the Luminy campus after an early morning run to the top of Mont Puget as we used to do on the previous workshop there. With versions of PDMP running on QMC (which makes sense when considering the deterministic component of the sampler).

Hastings at 50, from a Metropolis

Posted in Kids, pictures, Running, Travel with tags , , , , , , , , , , , , , , , , , , , , , , on January 4, 2020 by xi'an

A weekend trip to the quaint seaside city of Le Touquet Paris-Plage, facing the city of Hastings on the other side of the Channel, 50 miles away (and invisible on the pictures!), during and after a storm that made for a fantastic watch from our beach-side rental, if less for running! The town is far from being a metropolis, actually, but it got its added surname “Paris-Plage” from British investors who wanted to attract their countrymen in the late 1800s. The writers H.G. Wells and P.G. Wodehouse lived there for a while. (Another type of tourist, William the Conqueror, left for Hastings in 1066 from a wee farther south, near Saint-Valéry-sur-Somme.)

And the coincidental on-line publication in Biometrika of a 50 year anniversary paper, The Hastings algorithm at fifty by David Dunson and James Johndrow. More of a celebration than a comprehensive review, with focus on scalable MCMC, gradient based algorithms, Hamiltonian Monte Carlo, nonreversible Markov chains, and interesting forays into approximate Bayes. Which makes for a great read for graduate students and seasoned researchers alike!

Markov Chains [not a book review]

Posted in Books, pictures, Statistics, University life with tags , , , , , , , , , , , , , on January 14, 2019 by xi'an

As Randal Douc and Éric Moulines are both very close friends and two authors of this book on Markov chains,  I cannot engage into a regular book review! Judging from the table of contents, the coverage is not too dissimilar to the now classic Markov chain Stochastic Stability book by Sean Meyn and the late Richard Tweedie (1994), called the Bible of Markov chains by Peter Glynn, with more emphasis on convergence matters and a more mathematical perspective. The 757 pages book also includes a massive appendix on maths and probability background. As indicated in the preface, “the reason [the authors] thought it would be useful to write a new book is to survey some of the developments made during the 25 years that have elapsed since the publication of Meyn and Tweedie (1993b).” Connecting with the theoretical developments brought by MCMC methods. Like subgeometric rates of convergence to stationarity, sample paths, limit theorems, and concentration inequalities. The book also reflects on the numerous contributions of the authors to the field. Hence a perfect candidate for teaching Markov chains to mathematically well-prepared. graduate audiences. Congrats to the authors!

a conceptual introduction to HMC

Posted in Books, Statistics with tags , , , , , , , on September 5, 2017 by xi'an

“…it has proven a empirical success on an incredibly diverse set of target distributions encountered in applied problems.”

In January this year (!), Michael Betancourt posted on arXiv a detailed introduction to Hamiltonian Monte Carlo that recouped some talks of his I attended. Like the one in Boston two years ago. I have (re)read through this introduction to include an HMC section in my accelerating MCMC review for WIREs (which writing does not accelerate very much…)

“…this formal construction is often out of reach of theoretical and applied statisticians alike.”

With the relevant provision of Michael being a friend and former colleague at Warwick, I appreciate the paper at least as much as I appreciated the highly intuitive approach to HMC in his talks. It is not very mathematical and does not provide theoretical arguments for the defence of one solution versus another, but it (still) provides engaging reasons for using HMC.

“One way to ensure computational inefficiency is to waste computational resources evaluating the target density and relevant functions in regions of parameter space that have negligible contribution to the desired expectation.”

The paper starts by insisting on the probabilistic importance of the typical set, which amounts to a ring for Gaussian-like distributions. Meaning that in high dimensions the mode of the target is not a point that is particularly frequently visited.  I find this notion quite compelling and am at the same time [almost] flabbergasted that I have never heard of it before.

“we will consider only a single parameterization for computing expectations, but we must be careful to ensure that any such computation does not depend on the irrelevant details of that parameterization, such as the particular shape of the probability density function.”

I am not sure I get this sentence. Either it means that an expectation remains invariant under reparameterisation. Or something else and more profound that eludes me. In particular because Michael repeats later (p.25) that the canonical density does not depend on the parameterisation.

“Every choice of kinetic energy and integration time yields a new Hamiltonian transition that will interact differently with a given target distribution (…) when poorly-chosen, however, the performance can suffer dramatically.”

When discussing HMC, Michael tends to get a wee bit overboard with superlatives!, although he eventually points out the need for calibration as in the above quote. The explanation of the HMC move as a combination of uniform moves along isoclines of fixed energy level and of jumps between energy levels does not seem to translate into practical implementations, at least not as explained in the paper.  Simulating directly the energy distribution for a complex target distribution does not seem more feasible than moving up likelihood levels in nested sampling. (Unless I have forgotten something essential about HMC!) Similarly, when discussing symplectic integrators, the paper intuitively conveys the reason these integrators avoid Euler’s difficulties, even though one has to seek elsewhere for rigorous explanations. In the end I cannot but agree with the concluding statement that the geometry of the target distribution holds the key to devising more efficient Monte Carlo methods.

%d bloggers like this: