Multi-fidelity Batch Active Learning for Gaussian Process Classifiers
This work addresses the challenge of accelerating parameter space exploration in expensive computational simulations for science and engineering, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackled the problem of efficiently allocating simulation budgets in multi-fidelity settings using Gaussian Process classifiers, introducing the Bernoulli Parameter Mutual Information (BPMI) algorithm, which achieved higher predictive accuracy compared to baselines in synthetic and real-world experiments.
Many science and engineering problems rely on expensive computational simulations, where a multi-fidelity approach can accelerate the exploration of a parameter space. We study efficient allocation of a simulation budget using a Gaussian Process (GP) model in the binary simulation output case. This paper introduces Bernoulli Parameter Mutual Information (BPMI), a batch active learning algorithm for multi-fidelity GP classifiers. BPMI circumvents the intractability of calculating mutual information in the probability space by employing a first-order Taylor expansion of the link function. We evaluate BPMI against several baselines on two synthetic test cases and a complex, real-world application involving the simulation of a laser-ignited rocket combustor. In all experiments, BPMI demonstrates superior performance, achieving higher predictive accuracy for a fixed computational budget.