Fast Information-theoretic Bayesian Optimisation

Abstract

Information-theoretic Bayesian optimisation techniques have demonstrated state-of-the-art performance in tackling important global optimisation problems. However, current information-theoretic approaches require many approximations in implementation, introduce often-prohibitive computational overhead and limit the choice of kernels available to model the objective. We develop a fast information-theoretic Bayesian Optimisation method, FITBO, that avoids the need for sampling the global minimiser, thus significantly reducing computational overhead. Moreover, in comparison with existing approaches, our method faces fewer constraints on kernel choice and enjoys the merits of dealing with the output space. We demonstrate empirically that FITBO inherits the performance associated with information-theoretic Bayesian optimisation, while being even faster than simpler Bayesian optimisation approaches, such as Expected Improvement.

Main Paper: 9 pages, 6 figures, 2 tables; Accepted by ICML 2018

Cited by in corpus (12)

• Bayesian Optimization with Output-Weighted Optimal Sampling
• Applying Bayesian Analysis Guidelines to Empirical Software Engineering Data: The Case of Programming Languages and Code Quality
• Multi-fidelity Bayesian Optimization with Max-value Entropy Search and its parallelization
• Bayesian Optimisation over Multiple Continuous and Categorical Inputs
• Knowing The What But Not The Where in Bayesian Optimization
• Corruption-Tolerant Gaussian Process Bandit Optimization
• GIBBON: General-purpose Information-Based Bayesian OptimisatioN
• Bayesian Optimization for Iterative Learning
• Practical Batch Bayesian Optimization for Less Expensive Functions
• Marginalising over Stationary Kernels with Bayesian Quadrature
• Trusted-Maximizers Entropy Search for Efficient Bayesian Optimization
• Bayesian Optimization using Pseudo-Points