Archive for ABC

ABC in Stockholm [on-board again]

Posted in Kids, pictures, Statistics, Travel, University life with tags , , , , , , , , , , , , , , , , on May 18, 2016 by xi'an

abcruiseAfter a smooth cruise from Helsinki to Stockholm, a glorious sunrise over the Ålend Islands, and a morning break for getting an hasty view of the city, ABC in Helsinki (a.k.a. ABCruise) resumed while still in Stockholm. The first talk was by Laurent Calvet about dynamic (state-space) models, when the likelihood is not available and replaced with a proximity between the observed and the simulated observables, at each discrete time in the series. The authors are using a proxy predictive for the incoming observable and derive an optimal—in a non-parametric sense—bandwidth based on this proxy. Michael Gutmann then gave a presentation that somewhat connected with his talk at ABC in Roma, and poster at NIPS 2014, about using Bayesian optimisation to reduce the rejections in ABC algorithms. Which means building a model of a discrepancy or distance by Bayesian optimisation. I definitely like this perspective as it reduces the simulation to one of a discrepancy (after a learning step). And does not require a threshold. Aki Vehtari expanded on this idea with a series of illustrations. A difficulty I have with the approach is the construction of the acquisition function… The last session while pretty late was definitely exciting with talks by Richard Wilkinson on surrogate or emulator models, which goes very much in a direction I support, namely that approximate models should be accepted on their own, by Julien Stoehr with clustering and machine learning tools to incorporate more summary statistics, and Tim Meeds who concluded with two (small) talks!, centred on the notion of deterministic algorithms that explicitly incorporate the random generators within the comparison, resulting in post-simulation recentering à la Beaumont et al. (2003), plus new advances with further incorporations of those random generators turned deterministic functions within variational Bayes inference

On Wednesday morning, we will land back in Helsinki and head back to our respective homes, after another exciting ABC in… workshop. I am terribly impressed by the way this workshop at sea operated, providing perfect opportunities for informal interactions and collaborations, without ever getting claustrophobic or dense. Enjoying very long days also helped. While it seems unlikely we can repeat this successful implementation, I hope we can aim at similar formats in the coming occurrences. Kitos paljon to our Finnish hosts!

sunrise on Bothnia

Posted in Running, Travel, pictures with tags , , , , , , , , on May 17, 2016 by xi'an

ABC in Helsinki [on-board]

Posted in pictures, Statistics, Travel, University life with tags , , , , , , , , , , , , , , on May 17, 2016 by xi'an

abcruiseABC in Helsinki (a.k.a. ABCruise) has started! With a terrific weather most adequate for a cruise on the Baltic. The ship on which the workshop takes place is certainly larger than any I have been on, including the Channel ferries, and the inside alley looks rather like a shopping centre! However, the setting is exceptional, with comfy sea-facing cabins and pleasant breaks (including fancy tea!) Plus,  we have a quiet and cosy conference room that makes one forgets one is on a boat. Until it starts rocking. Or listing! The cruise boat is definitely large enough to be fairly stable. A unique experience we could consider for future (AB-see) workshops (with the caveat that we benefited from exceptional circumstances that brought the costs down to ridiculous amounts).

Richard Everitt talked about the synthetic likelihood approach and its connection with ABC. Making clear for me a point I had somewhat forgotten, namely that the approximative likelihood is a Gaussian at the observed summary statistics, but one centred at empirical moments derived from the simulation of pseudo summaries based on a given value of the parameter θ. So it is not an exact approach in that it does not converge to the true likelihood as the number of simulation grows to infinity. (While a kernel would converge.) That means it may (will) misrepresent the tails unless the distribution of the summary statistic is close to Normal. Richard also introduced bootstrap or bags of little bootstraps in order to speed up the generation of the pseudo-data, which makes sense albeit it moves the sampling away from the true model since it is conditional on  a single simulation.

Jean-Michel Marin introduced the ABC inference algorithm we are currently working on, using regression random forests that differ from the classification forests we used for model selection. (The paper is close to completion so I hope to be able to tell more in a near future!) Clara Grazian presented her semi-parametric work using ABC with Brunero Liseo. That was part of her thesis. Thomas Schön presented an extension of his particle Gibbs with adaptive sampling to the case of degenerate transitions, using an ABC approximation to get around this central problem. A very interesting entry that I need to study deeper. And Caroline Colijn talked about ABC for trees, mostly about the selection of summary statistics towards comparing tree topologies, with  a specific distance between trees that caters to the topology and only the topology.

ignorami rule

Posted in Kids, Travel, University life with tags , , , , , on May 12, 2016 by xi'an

plane2There has already been many blog entries [incl. Andrew’s] on that story of a plane passenger calling security about a neighbour solving differential equations next seat and many jokes will certainly stem from it. My closest encounter with such a passenger was a while ago, when flying to Manchester for a visit to Lancaster, when the man next to me suddenly asked if I was working on particle physics because he would not tolerate it. Or something like this. As I did not want to get arrested upon arrival I refrained from smashing his head into the seat and muttered something indistinct between a curse and a comment that this was statistics, but I now regret I had not confronted this holier-than-thou (to keep polite) attitude! This story also reminds me of another flight, from Montpelier to Paris, when I was discussing ABC with Jean-Michel Marin and Jean-Marie Cornuet, when an AF flight attendant came by and added an x at random in one of my equations! This did not solve the problem but we had a good laugh and did not end up questioned by security!

Anyway, my reaction to this PDE (or is it ODE?!) scandal is of a more sombre tone: I find the fact that airline personal paid any attention to the complaint deeply worrying. Rather that dismissing the worries of this ignorant (or myopic) passenger [and possibly contacting a psychiatrist], they called security and the PDE had to be produced before the economics professor could resume his seat and the flight take off… This incident shows both (i) a trend in irrationality (if associating maths equations with terrorist threat) or ignorance (if confusing maths equation with Arabic writing), not to mention xenophobia and (ii) a readiness of companies and administrations to pester, detain, question and bother anyone with any exotic characteristics. Including solving PDEs or even trying to. [But what can we expect when bottled water or orange marmalade is treated as a potential threat by security checks?] Beside sticking to writing maths in my notebook when I travel, I think I should start signalling to flight attendants truly irrational behaviours of my fellow passengers, like reading newspapers that seem solely concerned by the anatomy of reality TV shows or muttering prayers to a deity at take-off and landing…

auxiliary variable methods as ABC

Posted in Books, pictures, Statistics, University life with tags , , , , , on May 9, 2016 by xi'an

ruins of the abbey at Tynemouth, Sept. 03, 2013Dennis Prangle and Richard Everitt arXived a note today where they point out the identity between the auxiliary variable approach of Møller et al. (2006) [or rather its multiple or annealed version à la Murray] and [exact] ABC (as in our 2009 paper) in the case of Markov random fields. The connection between the two appears when using an importance sampling step in the ABC algorithm and running a Markov chain forward and backward the same number of steps as there are levels in the annealing scheme of MAV. Maybe more a curiosity than an indicator of a large phenomenon, since it is so rare that ABC can be use in its exact form.

ABC in Sevilla

Posted in pictures, Running, Travel with tags , , , , , on May 6, 2016 by xi'an

ABC for repulsive point processes

Posted in Books, pictures, Statistics, University life with tags , , , , , , , on May 5, 2016 by xi'an

garden tree, Jan. 12, 2012Shinichiro Shirota and Alan Gelfand arXived a paper on the use of ABC for analysing some repulsive point processes, more exactly the Gibbs point processes, for which ABC requires a perfect sampler to operate, unless one is okay with stopping an MCMC chain before it converges, and determinantal point processes studied by Lavancier et al. (2015) [a paper I wanted to review and could not find time to!]. Detrimental point processes have an intensity function that is the determinant of a covariance kernel, hence repulsive. Simulation of a determinantal process itself is not straightforward and involves approximations. But the likelihood itself is unavailable and Lavancier et al. (2015) use approximate versions by fast Fourier transforms, which means MCMC is challenging even with those approximate steps.

“The main computational cost of our algorithm is simulation of x for each iteration of the ABC-MCMC.”

The authors propose here to use ABC instead. With an extra approximative step for simulating the determinantal process itself. Interestingly, the Gibbs point process allows for a sufficient statistic, the number of R-closed points, although I fail to see how the radius R is determined by the model, while the determinantal process does not. The summary statistics end up being a collection of frequencies within various spheres of different radii. However, these statistics are then processed by Fearnhead’s and Prangle’s proposal, namely to come up as an approximation of E[θ|y] as the natural summary. Obtained by regression over the original summaries. Another layer of complexity stems from using an ABC-MCMC approach. And including a Lasso step in the regression towards excluding less relevant radii. The paper also considers Bayesian model validation for such point processes, implementing prior predictive tests with a ranked probability score, rather than a Bayes factor.

As point processes have always been somewhat mysterious to me, I do not have any intuition about the strength of the distributional assumptions there and the relevance of picking a determinantal process against, say, a Strauss process. The model comparisons operated in the paper are not strongly supporting one repulsive model versus the others, with the authors concluding at the need for many points towards a discrimination between models. I also wonder at the possibility of including other summaries than Ripley’s K-functions, which somewhat imply a discretisation of the space, by concentric rings. Maybe using other point processes for deriving summary statistics as MLEs or Bayes estimators for those models would help. (Or maybe not.)

Follow

Get every new post delivered to your Inbox.

Join 1,034 other followers