Archive for Coventry
off to Durham
Posted in Kids, pictures, Statistics, Travel, University life with tags #ERCSyG, Cambridge, collegial university, Coventry, Duke University, Durham, Durham university, England, ERC, Newcastle-upon-Tyne, North Carolina, Ocean, Oxford, The North, USA, warwick university on August 31, 2026 by xi'an
new ALPS
Posted in Books, pictures, Statistics, Travel, University life with tags Alps, annealed importance sampling, annealed leap-point sampler, Coventry, ICML 2026, University of Warwick, warm start on May 18, 2026 by xi'an
This morning, in Coventry, Hugo Queniat presesented Sampling from multimodal distributions with warm starts: Non-asymptotic bounds for the Reweighted Annealed Leap-Point Sampler by Holden Lee and Matheau Santana-Gijzen at a weekly reading group in Warwick. This fairly involved proposal is a modification of the original ALPS algorithm of (my friends) Nick Tawn (Warwick), Matt Moores (ex-Warwick), and Gareth Roberts (Warwick). With theoretical improvements but little applicability in realistic settings, imho (and in others). Still a fascinating topic!
likelihood-free posterior density learning at OWABI [30 April, 1pm GMT+1, 2pm CEST, 8am EST]
Posted in pictures, Running, Statistics, Travel, University life with tags ABC, Approximate Bayesian computation, Columbus, Coventry, dawn, deep learning, generative model, intractable likelihood, KASPE, Kenilworth, likelihood-free inference, Ohio State University, OWABI, posterior distribution, simulation-based inference, University of Warwick, webinar on April 17, 2026 by xi'an
The next OWABI webinar will take place on 30 April, at 1pm Coventry time (2pm in Paris, 8am in Columbus, Ohio) and will feature
Oksana A. Chkrebtii (Ohio State University)
Likelihood-free Posterior Density Learning for Uncertainty Quantification in Inference Problems
Generative models and those with computationally intractable likelihoods are widely used to describe complex systems in the natural sciences, social sciences, and engineering. Fitting these models to data requires likelihood-free inference methods that explore the parameter space without explicit likelihood evaluations, relying instead on sequential simulation, which comes at the cost of computational efficiency and extensive tuning. We develop an alternative framework called kernel-adaptive synthetic posterior estimation (KASPE) that uses deep learning to directly reconstruct the mapping between the observed data and a finite-dimensional parametric representation of the posterior distribution, trained on a large number of simulated datasets. We provide theoretical justification for KASPE and a formal connection to the likelihood-based approach of expectation propagation. Simulation experiments demonstrate KASPE’s flexibility and performance relative to existing likelihood-free methods including approximate Bayesian computation in challenging inferential settings involving posteriors with heavy tails, multiple local modes, and over the parameters of a nonlinear dynamical system.
European Meeting of Statisticians, Lugano, 24-28 Aug 2026
Posted in Statistics with tags 35th European Meeting of Statisticians, Bernoulli society, Coventry, EMS 2026, EMS 2028, England, Lago di Lugano, Lugano, Switzerland, Ticino, Università della Svizzera italiana, University of Warwick on February 18, 2026 by xi'an
statistics summer school at Warwick (July 2026)
Posted in Statistics, Travel, University life with tags algorithmic robustness, Britain, conformal prediction, course, Coventry, CRiSM, data contamination, data privacy, differential privacy, distribution-free inference, London Mathematical Society, on robust statistics, plenary speaker, reliable algorithms, summer course, University of Warwick on November 26, 2025 by xi'an
