Abstract
A fundamental issue in active learning of Gaussian processes is that of the explorationexploitation trade-off. This paper presents a novel nonmyopic ε-Bayes-optimal active learning (ε-BAL) approach that jointly and naturally optimizes the trade-off. In contrast, existing works have primarily developed myopic/greedy algorithms or performed exploration and exploitation separately. To perform active learning in real time, we then propose an anytime algorithm based on ε-BAL with performance guarantee and empirically demonstrate using synthetic and real-world datasets that, with limited budget, it outperforms the state-of-the-art algorithms.