Parallel Predictive Entropy Search for Batch Global Optimization of Expensive Objective Functions

By Amar Shah, Zoubin Ghahramani. 2015

169 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

In Management Science and Operations Research

Citations in the corpus

Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules (2019, methodology): “Other methods incorporate parallelization or use non-bayesian techniques (Li et al., 2016; Golovin et al., 2017; Shah & Ghahramani, 2015; Springenberg et al., 2016; Gonz´alez et al., 2016) but still either require multiple rounds of optimization or large amounts of compute.”
Population Based Training of Neural Networks (2017, background): “…attempting to parallelise them – training independent models in parallel to quicker update the Bayesian model (though potentially introducing bias) (Shah & Ghahramani, 2015; Gonz ´ alez et al., 2016; Wu & Frazier, 2016; Rasley et al., 2017; Golovin et al., 2017) – but these will still require…”
The Parallel Knowledge Gradient Method for Batch Bayesian Optimization (2016, methodology): “Other recent papers that value points collectively include [2] which optimizes the parallel EI by a closed-form formula, [15, 26], in which gradient-based methods are proposed to jointly optimize a parallel EI criterion, and [18], which proposes a parallel version of the ES algorithm and uses Monte ”
Maximizing acquisition functions for Bayesian optimization (2018, background): “In general however, we require that v min = min x ∈X ˆ (cid:96) ( f k ( x )) is guaranteed to be bounded from below for all functions under the support of p ( f”
Asynchronous Parallel Bayesian Optimisation via Thompson Sampling (2017, methodology): “Hence, there has been a ﬂurry of recent activity in this area [7, 8, 10, 12, 17, 24, 34, 38–40].”
Scalable Global Optimization via Local Bayesian Optimization (2019, background): “While several batch acquisition functions have recently been proposed [9, 40, 50, 54, 55, 28, 18], these approaches do not scale to large batch sizes in practice.”
Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space (2017, background): “Shah & Ghahramani (2015) extend the Predictive Entropy Search (PES) heuristic to the parallel setting (PPES).”
Constrained Bayesian Optimization with Noisy Experiments (2017, background): “Predictive entropy search has been discussed in the context of noise, constraints, and batch optimization (Hern´andez-Lobato et al. 2014, 2015, Shah and Ghahramani 2015).”
Recent Advances in Bayesian Optimization (2022, methodology): “In [287], unknown functions with varying fi-delities are jointly modeled as a convolved Gaussian process [5], then a multi-output random feature approximation is introduced to calculate PES.”
Parallelised Bayesian Optimisation via Thompson Sampling (2018, methodology): “Some methods become computationally prohibitive when there are a large number of workers and must resort to approximations [19, 38, 43, 46].”