Parallel Predictive Entropy Search for Batch Global Optimization of Expensive Objective Functions
This addresses the challenge of efficiently optimizing expensive functions in parallel for domains like machine learning and robotics, offering a novel non-greedy approach where previous methods were greedy.
The paper tackled the problem of batch selection in Bayesian optimization for expensive black-box functions by developing PPES, a non-greedy algorithm that selects batches to maximize information gain about the global maximizer, and demonstrated improved optimization performance on synthetic and real-world applications.
We develop parallel predictive entropy search (PPES), a novel algorithm for Bayesian optimization of expensive black-box objective functions. At each iteration, PPES aims to select a batch of points which will maximize the information gain about the global maximizer of the objective. Well known strategies exist for suggesting a single evaluation point based on previous observations, while far fewer are known for selecting batches of points to evaluate in parallel. The few batch selection schemes that have been studied all resort to greedy methods to compute an optimal batch. To the best of our knowledge, PPES is the first non-greedy batch Bayesian optimization strategy. We demonstrate the benefit of this approach in optimization performance on both synthetic and real world applications, including problems in machine learning, rocket science and robotics.