Variational Bayesian Optimal Experimental Design

Abstract

Bayesian optimal experimental design (BOED) is a principled framework for making efficient use of limited experimental resources. Unfortunately, its applicability is hampered by the difficulty of obtaining accurate estimates of the expected information gain (EIG) of an experiment. To address this, we introduce several classes of fast EIG estimators by building on ideas from amortized variational inference. We show theoretically and empirically that these estimators can provide significant gains in speed and accuracy over previous approaches. We further demonstrate the practicality of our approach on a number of end-to-end experiments.

Published as a conference paper at the Thirty-third Conference on Neural Information Processing Systems, Vancouver 2019. https://papers.nips.cc/paper/9553-variational-bayesian-optimal-experimental-design.pdf

Cited by in corpus (11)

• Noisy Adaptive Group Testing using Bayesian Sequential Experimental Design
• Unbiased MLMC stochastic gradient-based optimization of Bayesian experimental designs
• Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design
• Bayesian Experimental Design for Implicit Models by Mutual Information Neural Estimation
• Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoods
• Gradient-based Bayesian Experimental Design for Implicit Models using Mutual Information Lower Bounds
• A Scalable Gradient-Free Method for Bayesian Experimental Design with Implicit Models
• Using Gaussian Processes to Design Dynamic Experiments for Black-Box Model Discrimination under Uncertainty
• Learning Arbitrary Quantities of Interest from Expensive Black-Box Functions through Bayesian Sequential Optimal Design
• Targeted Active Learning for Bayesian Decision-Making
• A Hybrid Gradient Method to Designing Bayesian Experiments for Implicit Models