Distributionally Robust Bayesian Quadrature Optimization
Nguyen, Thanh Tang, Gupta, Sunil, Ha, Huong, Rana, Santu, Venkatesh, Svetha
Bayesian quadrature optimization (BQO) maximizes the expectation of an expensive black-box integrand taken over a known probability distribution. In this work, we study BQO under distributional uncertainty in which the underlying probability distribution is unknown except for a limited set of its i.i.d. samples. A standard BQO approach maximizes the Monte Carlo estimate of the true expected objective given the fixed sample set. Though Monte Carlo estimate is unbiased, it has high variance given a small set of samples; thus can result in a spurious objective function. We adopt the distributionally robust optimization perspective to this problem by maximizing the expected objective under the most adversarial distribution. In particular, we propose a novel posterior sampling based algorithm, namely distributionally robust BQO (DRBQO) for this purpose. We demonstrate the empirical effectiveness of our proposed framework in synthetic and real-world problems, and characterize its theoretical convergence via Bayesian regret.
Jan-19-2020
- Country:
- Asia > South Korea
- Jeollanam-do > Muan (0.04)
- Europe > Italy
- Oceania > Australia (0.14)
- Asia > South Korea
- Genre:
- Research Report (1.00)
- Technology: