English

Distributionally Robust Bayesian Quadrature Optimization

Machine Learning 2020-01-22 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2001.06814,
  title  = {Distributionally Robust Bayesian Quadrature Optimization},
  author = {Thanh Tang Nguyen and Sunil Gupta and Huong Ha and Santu Rana and Svetha Venkatesh},
  journal= {arXiv preprint arXiv:2001.06814},
  year   = {2020}
}

Comments

AISTATS2020

R2 v1 2026-06-23T13:14:59.246Z