Efficient acquisition rules for model-based approximate Bayesian computation
arXiv:1704.00520 · doi:10.1214/18-BA1121
Abstract
Approximate Bayesian computation (ABC) is a method for Bayesian inference when the likelihood is unavailable but simulating from the model is possible. However, many ABC algorithms require a large number of simulations, which can be costly. To reduce the computational cost, Bayesian optimisation (BO) and surrogate models such as Gaussian processes have been proposed. Bayesian optimisation enables one to intelligently decide where to evaluate the model next but common BO strategies are not designed for the goal of estimating the posterior distribution. Our paper addresses this gap in the literature. We propose to compute the uncertainty in the ABC posterior density, which is due to a lack of simulations to estimate this quantity accurately, and define a loss function that measures this uncertainty. We then propose to select the next evaluation location to minimise the expected loss. Experiments show that the proposed method often produces the most accurate approximations as compared to common BO strategies.
arXiv comment30 pages, 10 figures
References in corpus (21)
- Practical Bayesian Optimization of Machine Learning Algorithms
- Approximate Bayesian computation scheme for parameter inference and model selection in dynamical systems
- Adaptive approximate Bayesian computation
- Non-linear regression models for Approximate Bayesian Computation
- Predictive Entropy Search for Efficient Global Optimization of Black-box Functions
- A Comparative Review of Dimension Reduction Methods in Approximate Bayesian Computation
- Approximate Bayesian computation (ABC) gives exact results under the assumption of model error
- Max-value Entropy Search for Efficient Bayesian Optimization
- Adaptive approximate Bayesian computation for complex models
- Fast -free Inference of Simulation Models with Bayesian Conditional Density Estimation
- Probabilistic Numerics and Uncertainty in Computations
- Slice sampling covariance hyperparameters of latent Gaussian models
- GPS-ABC: Gaussian Process Surrogate Approximate Bayesian Computation
- Bayesian Optimization for Likelihood-Free Inference of Simulator-Based Statistical Models
- Accelerating ABC methods using Gaussian processes
- GLASSES: Relieving The Myopia Of Bayesian Optimisation
- Efficient acquisition rules for model-based approximate Bayesian computation
- Unbounded Bayesian Optimization via Regularization
- Optimization as Estimation with Gaussian Processes in Bandit Settings
- A sequential Monte Carlo approach to Thompson sampling for Bayesian optimization
- A comparison of emulation methods for Approximate Bayesian Computation
Cited by in corpus (8)
- General framework for cosmological dark matter bounds using -body simulations
- Efficient acquisition rules for model-based approximate Bayesian computation
- Sequential Bayesian experimental design for calibration of expensive simulation models
- Bridging the reality gap in quantum devices with physics-aware machine learning
- A survey of Monte Carlo methods for noisy and costly densities with application to reinforcement learning and ABC
- Parametric scaling of power exhaust in EU-DEMO alternative divertor simulations
- Sequentially guided MCMC proposals for synthetic likelihoods and correlated synthetic likelihoods
- Uncertainty Quantification in Breakup Reactions