Nonmyopic ϵ-Bayes-Optimal Active Learning of Gaussian Processes
Author(s)
Hoang, Trong Nghia; Low, Bryan Kian Hsiang; Jaillet, Patrick; Kankanhalli, Mohan
DownloadJaillet_Nonmyopic.pdf (886.2Kb)
PUBLISHER_POLICY
Publisher Policy
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Terms of use
Metadata
Show full item recordAbstract
A fundamental issue in active learning of Gaussian processes is that of the exploration-exploitation 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.
Date issued
2014Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer ScienceJournal
Proceedings of the 31st International Conference on Machine Learning
Publisher
Association for Computing Machinery (ACM)
Citation
Hoang, Trong Nghia, Bryan Kian Hsiang Low, Patrick Jaillet, and Mohan Kankanhalli. "Nonmyopic ϵ-Bayes-Optimal Active Learning of Gaussian Processes." 31st International Conference on Machine Learning (2014).
Version: Author's final manuscript
ISSN
1938-7228