Multifidelity Approximate Bayesian Computation with Sequential Monte Carlo Parameter Sampling
arXiv:2001.06256 · doi:10.1137/20M1316160
Abstract
Multifidelity approximate Bayesian computation (MF-ABC) is a likelihood-free technique for parameter inference that exploits model approximations to significantly increase the speed of ABC algorithms (Prescott and Baker, 2020). Previous work has considered MF-ABC only in the context of rejection sampling, which does not explore parameter space particularly efficiently. In this work, we integrate the multifidelity approach with the ABC sequential Monte Carlo (ABC-SMC) algorithm into a new MF-ABC-SMC algorithm. We show that the improvements generated by each of ABC-SMC and MF-ABC to the efficiency of generating Monte Carlo samples and estimates from the ABC posterior are amplified when the two techniques are used together.
References in corpus (15)
- Approximate Bayesian computation scheme for parameter inference and model selection in dynamical systems
- Low Dimensional Behavior of Large Systems of Globally Coupled Oscillators
- Adaptive approximate Bayesian computation
- Long Time Evolution of Phase Oscillator Systems
- Approximation and inference methods for stochastic biochemical kinetics - a tutorial review
- On Russian Roulette Estimates for Bayesian Inference with Doubly-Intractable Likelihoods
- Rethinking the Effective Sample Size
- Efficient white noise sampling and coupling for multilevel Monte Carlo with non-nested meshes
- Multilevel rejection sampling for approximate Bayesian computation
- Multifidelity Approximate Bayesian Computation
- Accelerating inference for diffusions observed with measurement error and large sample sizes using Approximate Bayesian Computation
- Optimal proposals for Approximate Bayesian Computation
- Robustly simulating biochemical reaction kinetics using multi-level Monte Carlo approaches
- Learning Negative Mixture Models by Tensor Decompositions
- Multilevel Monte Carlo in Approximate Bayesian Computation