The Parallel Knowledge Gradient Method for Batch Bayesian Optimization
This work addresses the need for efficient batch optimization in parallel computing environments, such as tuning hyperparameters in machine learning, and is incremental as it builds on existing Bayesian optimization methods.
The paper tackles the problem of batch Bayesian optimization for parallel evaluation scenarios, introducing the parallel knowledge gradient method which is shown to find global optima significantly faster than previous algorithms, particularly in noisy conditions.
In many applications of black-box optimization, one can evaluate multiple points simultaneously, e.g. when evaluating the performances of several different neural network architectures in a parallel computing environment. In this paper, we develop a novel batch Bayesian optimization algorithm --- the parallel knowledge gradient method. By construction, this method provides the one-step Bayes-optimal batch of points to sample. We provide an efficient strategy for computing this Bayes-optimal batch of points, and we demonstrate that the parallel knowledge gradient method finds global optima significantly faster than previous batch Bayesian optimization algorithms on both synthetic test functions and when tuning hyperparameters of practical machine learning algorithms, especially when function evaluations are noisy.