keep thunderbird alive!

Monte Carlo fusion

Hongsheng Dai, Murray Pollock (University of Warwick), and Gareth Roberts (University of Warwick) just arXived a paper we discussed together last year while I was at Warwick. Where fusion means bringing different parts of the target distribution

f(x)∝f¹(x)f²(x)…

together, once simulation from each part has been done. In the same spirit as in Scott et al. (2016) consensus Monte Carlo. Where for instance the components of the target cannot be computed simultaneously, either because of the size of the dataset, or because of privacy issues.The idea in this paper is to target an augmented density with the above marginal, using for each component of f, an auxiliary variable x¹,x²,…, and a target that is the product of the squared component, f¹(x¹)², f²(x²)², … by a transition density keeping f¹(.)²,f²(.)²,… invariant:

as for instance the transition density of a Langevin diffusion. The marginal of

as a function of y is then the targeted original product. Simulating from this new extended target can be achieved by rejection sampling. (Any impact of the number of auxiliary variables on the convergence?) The practical implementation actually implies using the path-space rejection sampling methods in the Read Paper of Beskos et al. (2006). (An extreme case of the algorithm is actually an (exact) ABC version where the simulations x¹,x²,… from all components have to be identical and equal to y. The opposite extreme is the consensus Monte Carlo Algorithm, which explains why this algorithm is not an efficient solution.) An alternative is based on an Ornstein-Uhlenbeck bridge. While the paper remains at a theoretical level with toy examples, I heard from the same sources that applications to more realistic problems and implementation on parallel processors is under way.

GDPR fatigue

intractable likelihoods (even) for Alan

In connection with the official launch of the Alan Turing Institute (or ATI, of which Warwick is a partner), it funded an ATI Scoping workshop yesterday a week ago in Warwick around the notion(s) of intractable likelihood(s) and how this could/should fit within the themes of the Institute [hence the scoping]. This is one among many such scoping workshops taking place at all partners, as reported on the ATI website. Workshop that was quite relaxed and great fun, if only for getting together with most people (and friends) in the UK interested in the topic. But also pointing out some new themes I had not previously though of as related to ilike. For instance, questioning the relevance of likelihood for inference and putting forward decision theory under model misspecification, connecting with privacy and ethics [hence making intractable “good”!], introducing uncertain likelihood, getting more into network models, RKHS as a natural summary statistic, swarm of solutions for consensus inference… (And thanks to Mark Girolami for this homage to the iconic LP of the Sex Pistols!, that I played maniacally all over 1978…) My own two-cents into the discussion were mostly variations of other discussions, borrowing from ABC (and ABC slides) to call for a novel approach to approximate inference:

methods for quantifying conflict casualties in Syria

On Monday November 17, 11am, Amphi 10, Université Paris-Dauphine,  Rebecca Steorts from CMU will give a talk at the GT Statistique et imagerie seminar:

Information about social entities is often spread across multiple large databases, each degraded by noise, and without unique identifiers shared across databases.Entity resolution—reconstructing the actual entities and their attributes—is essential to using big data and is challenging not only for inference but also for computation.

In this talk, I motivate entity resolution by the current conflict in Syria. It has been tremendously well documented, however, we still do not know how many people have been killed from conflict-related violence. We describe a novel approach towards estimating death counts in Syria and challenges that are unique to this database. We first introduce computational speed-ups to avoid all-to-all record comparisons based upon locality-sensitive hashing from the computer science literature. We then introduce a novel approach to entity resolution by discovering a bipartite graph, which links manifest records to a common set of latent entities. Our model quantifies the uncertainty in the inference and propagates this uncertainty into subsequent analyses. Finally, we speak to the success and challenges of solving a problem that is at the forefront of national headlines and news.

This is joint work with Rob Hall (Etsy), Steve Fienberg (CMU), and Anshu Shrivastava (Cornell University).

[Note that Rebecca will visit the maths department in Paris-Dauphine for two weeks and give a short course in our data science Master on data confidentiality, privacy and statistical disclosure (syllabus).]