Bayesian Optimization for Likelihood-Free Inference of Simulator-Based Statistical Models

Abstract

Our paper deals with inferring simulator-based statistical models given some observed data. A simulator-based model is a parametrized mechanism which specifies how data are generated. It is thus also referred to as generative model. We assume that only a finite number of parameters are of interest and allow the generative process to be very general; it may be a noisy nonlinear dynamical system with an unrestricted number of hidden variables. This weak assumption is useful for devising realistic models but it renders statistical inference very difficult. The main challenge is the intractability of the likelihood function. Several likelihood-free inference methods have been proposed which share the basic idea of identifying the parameters by finding values for which the discrepancy between simulated and observed data is small. A major obstacle to using these methods is their computational cost. The cost is largely due to the need to repeatedly simulate data sets and the lack of knowledge about how the parameters affect the discrepancy. We propose a strategy which combines probabilistic modeling of the discrepancy with optimization to facilitate likelihood-free inference. The strategy is implemented using Bayesian optimization and is shown to accelerate the inference through a reduction in the number of required simulations by several orders of magnitude.

In press with the Journal of Machine Learning Research (JMLR). Accepted August 17, 2015

References in corpus (3)

• Practical Bayesian Optimization of Machine Learning Algorithms
• A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
• High Dimensional Bayesian Optimisation and Bandits via Additive Models

Cited by in corpus (19)

• The frontier of simulation-based inference
• Cumulative effects of triadic closure and homophily in social networks
• Bayesian optimisation for likelihood-free cosmological inference
• Bayesian emulator optimisation for cosmology: application to the Lyman-alpha forest
• Variational Bayes with Synthetic Likelihood
• Inferring Cognitive Models from Data using Approximate Bayesian Computation
• Cosmological parameter estimation via iterative emulation of likelihoods
• Efficient acquisition rules for model-based approximate Bayesian computation
• ELFI: Engine for Likelihood-Free Inference
• Prepaid parameter estimation without likelihoods
• Approximating Bayes in the 21st Century
• Optimization Monte Carlo: Efficient and Embarrassingly Parallel Likelihood-Free Inference
• ABCpy: A High-Performance Computing Perspective to Approximate Bayesian Computation
• Inverse Reinforcement Learning from Summary Data
• A survey of Monte Carlo methods for noisy and costly densities with application to reinforcement learning and ABC
• Sequentially guided MCMC proposals for synthetic likelihoods and correlated synthetic likelihoods
• Distance-learning For Approximate Bayesian Computation To Model a Volcanic Eruption
• Approximate methods for dynamic ecological models
• Classification and Bayesian Optimization for Likelihood-Free Inference