Archive for England
I had quite a special day today as I travelled through Birmingham, made a twenty minutes stop in Coventry to drop my bag in my office, went down to London to collect a most kindly loaned city-bike and took the train back to Coventry with the said bike… On my way from Bristol to Warwick, I decided to spend the night in downtown Birmingham as it was both easier and cheaper than to find accommodation on Warwick campus. However, while the studio I rented was well-designed and brand-new, my next door neighbours were not so well-designed in that I could hear them and the TV through the wall, despite top-quality ear-plugs! After a request of mine, they took the TV off but kept to the same decibel level for their uninteresting exchanges. In the morning I tried to go running in the centre of Birmingham but, as I could not find the canals, I quickly got bored and gave up. As Mark had proposed to lend me a city bike for my commuting in [and not to] Warwick, I then decided to take the opportunity of a free Sunday to travel down to London to pick the bike, change the pedals in a nearby shop, add an anti-theft device, and head back to Coventry. Which gave me the opportunity to bike in London by Abbey Road, Regent Park, and Hampstead, before [easily] boarding a fast train back to Coventry and biking up to the University of Warwick campus. (Sadly to discover that all convenience stores had closed by then… )
Last and maybe most exciting day of the “High-dimensional Stochastic Simulation and Optimisation in Image Processing” in Bristol as it was exclusively about simulation (MCMC) methods. Except my own talk on ABC. And Peter Green’s on consistency of Bayesian inference in non-regular models. The talks today were indeed about using convex optimisation devices to speed up MCMC algorithms with tools that were entirely new to me, like the Moreau transform discussed by Marcelo Pereyra. Or using auxiliary variables à la RJMCMC to bypass expensive Choleski decompositions. Or optimisation steps from one dual space to the original space for the same reason. Or using pseudo-gradients on partly differentiable functions in the talk by Sylvain Lecorff on a paper commented earlier in the ‘Og. I particularly liked the notion of Moreau regularisation that leads to more efficient Langevin algorithms when the target is not regular enough. Actually, the discretised diffusion itself may be geometrically ergodic without the corrective step of the Metropolis-Hastings acceptance. This obviously begs the question of an extension to Hamiltonian Monte Carlo. And to multimodal targets, possibly requiring as many normalisation factors as there are modes. So, in fine, a highly informative workshop, with the perfect size and the perfect crowd (which happened to be predominantly French, albeit from a community I did not have the opportunity to practice previously). Massive kudos to Marcello for putting this workshop together, esp. on a week where family major happy events should have kept him at home!
As the workshop ended up in mid-afternoon, I had plenty of time for a long run with Florence Forbes down to the Avon river and back up among the deers of Ashton Court, avoiding most of the rain, all of the mountain bikes on a bike trail that sounded like trail running practice, and building enough of an appetite for the South Indian cooking of the nearby Thali Café. Brilliant!
After a nice morning run down Leigh Woods and on the muddy banks of the Avon river, I attended a morning session on hyperspectral image non-linear modelling. Topic about which I knew nothing beforehand. Hyperspectral images are 3-D images made of several wavelengths to improve their classification as a mixture of several elements. The non-linearity is due to the multiple reflections from the ground as well as imperfections in the data collection. I found this new setting of clear interest, from using mixtures to exploring Gaussian processes and Hamiltonian Monte Carlo techniques on constrained spaces… Not to mention the “debate” about using Bayesian inference versus optimisation. It was overall a day of discovery as I am unaware of the image processing community (being the outlier in this workshop!) and of their techniques. The problems mostly qualify as partly linear high-dimension inverse problems, with rather standard if sometimes hybrid MCMC solutions. (The day ended even more nicely with another long run in the fields of Ashton Court and a conference diner by the river…)
Even though I flew through Birmingham (and had to endure the fundamental randomness of trains in Britain), I managed to reach the “High-dimensional Stochastic Simulation and Optimisation in Image Processing” conference location (in Goldney Hall Orangery) in due time to attend the (second) talk by Christophe Andrieu. He started with an explanation of the notion of controlled Markov chain, which reminded me of our early and famous-if-unpublished paper on controlled MCMC. (The label “controlled” was inspired by Peter Green who pointed out to us the different meanings of controlled in French [meaning checked or monitored] and in English . We use it here in the English sense, obviously.) The main focus of the talk was on the stability of controlled Markov chains. With of course connections with out controlled MCMC of old, for instance the case of the coerced acceptance probability. Which happened to be not that stable! With the central tool being Lyapounov functions. (Making me wonder whether or not it would make sense to envision the meta-problem of adaptively estimating the adequate Lyapounov function from the MCMC outcome.)
As I had difficulties following the details of the convex optimisation talks in the afternoon, I eloped to work on my own and returned to the posters & wine session, where the small number of posters allowed for the proper amount of interaction with the speakers! Talking about the relevance of variational Bayes approximations and of possible tools to assess it, about the use of new metrics for MALA and of possible extensions to Hamiltonian Monte Carlo, about Bayesian modellings of fMRI and of possible applications of ABC in this framework. (No memorable wine to make the ‘Og!) Then a quick if reasonably hot curry and it was already bed-time after a rather long and well-filled day!z
This introduction to Bayesian Analysis, Bayes’ Rule, was written by James Stone from the University of Sheffield, who contacted CHANCE suggesting a review of his book. I thus bought it from amazon to check the contents. And write a review.
First, the format of the book. It is a short paper of 127 pages, plus 40 pages of glossary, appendices, references and index. I eventually found the name of the publisher, Sebtel Press, but for a while thought the book was self-produced. While the LaTeX output is fine and the (Matlab) graphs readable, pictures are not of the best quality and the display editing is minimal in that there are several huge white spaces between pages. Nothing major there, obviously, it simply makes the book look like course notes, but this is in no way detrimental to its potential appeal. (I will not comment on the numerous appearances of Bayes’ alleged portrait in the book.)
“… (on average) the adjusted value θMAP is more accurate than θMLE.” (p.82)
Bayes’ Rule has the interesting feature that, in the very first chapter, after spending a rather long time on Bayes’ formula, it introduces Bayes factors (p.15). With the somewhat confusing choice of calling the prior probabilities of hypotheses marginal probabilities. Even though they are indeed marginal given the joint, marginal is usually reserved for the sample, as in marginal likelihood. Before returning to more (binary) applications of Bayes’ formula for the rest of the chapter. The second chapter is about probability theory, which means here introducing the three axioms of probability and discussing geometric interpretations of those axioms and Bayes’ rule. Chapter 3 moves to the case of discrete random variables with more than two values, i.e. contingency tables, on which the range of probability distributions is (re-)defined and produces a new entry to Bayes’ rule. And to the MAP. Given this pattern, it is not surprising that Chapter 4 does the same for continuous parameters. The parameter of a coin flip. This allows for discussion of uniform and reference priors. Including maximum entropy priors à la Jaynes. And bootstrap samples presented as approximating the posterior distribution under the “fairest prior”. And even two pages on standard loss functions. This chapter is followed by a short chapter dedicated to estimating a normal mean, then another short one on exploring the notion of a continuous joint (Gaussian) density.
“To some people the word Bayesian is like a red rag to a bull.” (p.119)
Bayes’ Rule concludes with a chapter entitled Bayesian wars. A rather surprising choice, given the intended audience. Which is rather bound to confuse this audience… The first part is about probabilistic ways of representing information, leading to subjective probability. The discussion goes on for a few pages to justify the use of priors but I find completely unfair the argument that because Bayes’ rule is a mathematical theorem, it “has been proven to be true”. It is indeed a maths theorem, however that does not imply that any inference based on this theorem is correct! (A surprising parallel is Kadane’s Principles of Uncertainty with its anti-objective final chapter.)
All in all, I remain puzzled after reading Bayes’ Rule. Puzzled by the intended audience, as contrary to other books I recently reviewed, the author does not shy away from mathematical notations and concepts, even though he proceeds quite gently through the basics of probability. Therefore, potential readers need some modicum of mathematical background that some students may miss (although it actually corresponds to what my kids would have learned in high school). It could thus constitute a soft entry to Bayesian concepts, before taking a formal course on Bayesian analysis. Hence doing no harm to the perception of the field.
My friend and Warwick colleague Gareth Roberts just published a paper in Nature with Ellen Brooks-Pollock and Matt Keeling from the University of Warwick on the modelling of bovine tuberculosis dynamics in Britain and on the impact of control measures. The data comes from the Cattle Tracing System and the VetNet national testing database. The mathematical model is based on a stochastic process and its six parameters are estimated by sequential ABC (SMC-ABC). The summary statistics chosen in the model are the number of infected farms per county per year and the number of reactors (cattle failing a test) per county per year.
“Therefore, we predict that control of local badger populations and hence control of environmental transmission will have a relatively limited effect on all measures of bovine TB incidence.”
This advanced modelling of a comprehensive dataset on TB in Britain quickly got into a high profile as it addresses the highly controversial (not to say plain stupid) culling of badgers (who also carry TB) advocated by the government. The study concludes that “only generic measures such as more national testing, whole herd culling or vaccination that affect all routes of transmission are effective at controlling the spread of bovine TB.” While the elimination of badgers from the English countryside would have a limited effect. Good news for badgers! And the Badger Trust. Unsurprisingly, the study was immediately rejected by the UK farming minister! Not only does he object to the herd culling solution for economic reasons, but he “cannot accept the paper’s findings”. Maybe he does not like ABC… More seriously, the media oversimplified the findings of the study, “as usual”, with e.g. The Guardian headline of “tuberculosis threat requires mass cull of cattle”.