Archive for approximate Bayesian inference

call for posters at BayesComp²³ satellite [AG:DC]

Posted in Mountains, pictures, Statistics, Travel, University life with tags , , , , , , , , , on November 22, 2022 by xi'an

An urgent reminder that the early bird deadline for BayesComp²³ and the different satellites is 30 November (with a difference of $50) and also a call for poster presentations at our AG:DC (aka, Bayesian computing without exact likelihood) satellite workshop. Poster spots will be attributed to presenters on a first come – first served basis, so do not delay in sending me an abstract at my gmail account bayesianstatistics

Frontiers in Machine Learning and Economics: Methods and Applications

Posted in Statistics with tags , , , , , , , , on October 7, 2022 by xi'an

invited sessions at BayesComp [submissions open]

Posted in Mountains, pictures, Statistics, Travel, University life with tags , , , , , , , on July 8, 2022 by xi'an

The call for invited sessions at BayesComp 2022 is now open, submission can be done via Google Form. Submissions are due by August 7. If you have any questions, please email to bayescomp2023 on Gmail. And if you want to contribute to AG::DC, please email Anto, Heikki or me!

nonparametric ABC [seminar]

Posted in pictures, Statistics, University life with tags , , , , , , , , , , , , , on June 3, 2022 by xi'an

Puzzle: How do you run ABC when you mistrust the model?! We somewhat considered this question in our misspecified ABC paper with David and Judith. An AISTATS 2022 paper by Harita Dellaporta (Warwick), Jeremias KnoblauchTheodoros Damoulas (Warwick), and François-Xavier Briol (formerly Warwick) is addressing this same question and Harita presented the paper at the One World ABC webinar yesterday.

It is inspired from Lyddon, Walker & Holmes (2018), who place a nonparametric prior on the generating model, in top of the assumed parametric model (with an intractable likelihood). This induces a push-forward prior on the pseudo-true parameter, that is, the value that brings the parametric family the closest possible to the true distribution of the data. Here defined as a minimum distance parameter, the maximum mean discrepancy (MMD). Choosing RKHS framework allows for a practical implementation, resorting to simulations for posterior realisations from a Dirichlet posterior and from the parametric model, and stochastic gradient for computing the pseudo-true parameter, which may prove somewhat heavy in terms of computing cost.

The paper also containts a consistency result in an ε-contaminated setting (contamination of the assumed parametric family). Comparisons like the above with a fully parametric Wasserstein-ABC approach show that this alter resists better misspecification, as could be expected since the later is not constructed for that purpose.

Next talk is on 23 June by Cosma Shalizi.

Recent Advances in Approximate Bayesian Inference [YSE, 15.2.22]

Posted in Statistics, University life with tags , , , , , on May 11, 2022 by xi'an


On June 15, the Young Statisticians Europe initiative is organising an on-line seminar on approximate Bayesian inference. With talks by

starting at 7:00 PT / 10:00 EST / 16:00 CET. The registration form is available here.

%d bloggers like this: