论文标题
分布强劲的贝叶斯优化
Distributionally Robust Bayesian Optimization
论文作者
论文摘要
分销转移的鲁棒性是当代机器学习的主要挑战之一。达到这种鲁棒性是分布鲁棒优化的目标，它寻求解决优化问题的解决方案，该优化问题在不受控制的协变量的指定分布变化下是最坏的。在本文中，我们研究了通过最大平均差异（MMD）测量分布变化时的问题。为了设置零阶噪声优化，我们提出了一种新颖的分布在稳健的贝叶斯优化算法（DRBO）。事实证明，我们的算法在各种环境中获得了下线稳健的后悔，这些遗憾在观察到不确定的协变量方面有所不同。我们证明了我们方法在合成和现实世界基准上的强大性能。
Robustness to distributional shift is one of the key challenges of contemporary machine learning. Attaining such robustness is the goal of distributionally robust optimization, which seeks a solution to an optimization problem that is worst-case robust under a specified distributional shift of an uncontrolled covariate. In this paper, we study such a problem when the distributional shift is measured via the maximum mean discrepancy (MMD). For the setting of zeroth-order, noisy optimization, we present a novel distributionally robust Bayesian optimization algorithm (DRBO). Our algorithm provably obtains sub-linear robust regret in various settings that differ in how the uncertain covariate is observed. We demonstrate the robust performance of our method on both synthetic and real-world benchmarks.
