Guided sequential ABC schemes for intractable Bayesian models
Preprint, 2023
We contribute to the ABC modeller’s toolbox with novel proposal samplers that are conditional to summary statistics of the data. In a sense, the proposed parameters are “guided” to rapidly reach regions of the posterior surface that are compatible with the observed data. This speeds up the convergence of these sequential samplers, thus reducing the computational effort, while preserving the accuracy in the inference. We provide a variety of guided Gaussian and copula-based samplers for both SIS-ABC and SMC-ABC easing inference for challenging case-studies, including multimodal posteriors, highly correlated posteriors, hierarchical models with high-dimensional summary statistics (180 summaries used to infer 21 parameters) and a simulation study of cell movements (using more than 400 summaries).
Approximate Bayesian computation
sequential importance sampling
copulas
sequential Monte Carlo
simulation-based inference
Författare
Umberto Picchini
Chalmers, Matematiska vetenskaper, Tillämpad matematik och statistik
Massimiliano Tamborrino
The University of Warwick
Statistisk inferensteori och stokastisk modellering av proteinveckning
Vetenskapsrådet (VR) (2013-5167), 2014-01-01 -- 2019-12-31.
Djupinlärning och likelihood-fri Bayesiansk inferens för stokastiska modeller
Chalmers AI-forskningscentrum (CHAIR), 2020-01-01 -- 2024-12-31.
Vetenskapsrådet (VR) (2019-03924), 2020-01-01 -- 2023-12-31.
Ämneskategorier
Sannolikhetsteori och statistik