arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.20145cs.LGstat.ML
收藏

面向任意不确定输入的高效鲁棒贝叶斯优化

Efficient Robust Bayesian Optimization for Arbitrary Uncertain Inputs

Huawei Noah’s Ark Lab(华为诺亚方舟实验室)

Lin Yang, Junlong Lyu, Wenlong Lyu, Zhitang Chen

AI总结:

针对贝叶斯优化中输入不确定性导致性能波动的问题,提出基于MMD和Nystrom近似的AIRBO算法,可处理任意分布的不确定输入,具备理论保证且性能达SOTA。

摘要:

贝叶斯优化(BO)是一种样本高效的优化算法,被广泛应用于各类场景中。在一些具有挑战性的BO任务中,优化过程中不可避免的随机性会带来输入不确定性,例如加工误差、执行噪声或环境可变性。这种不确定性会使输入在评估前偏离预期值,导致最终结果出现显著的性能波动。本文提出了一种新型鲁棒贝叶斯优化算法AIRBO,该算法能够有效识别在任意输入不确定性下性能始终稳定的鲁棒最优解。我们的方法通过为高斯过程引入最大均值差异(MMD),直接对任意分布的不确定输入进行建模,并通过Nystrom近似进一步加速后验推断。我们在MMD估计误差下建立了严格的理论后悔界,同时在合成函数和真实问题上开展的大量实验表明,该方法能够应对各类输入不确定性,并达到当前最优性能。

英文摘要:

Bayesian Optimization (BO) is a sample-efficient optimization algorithm widely employed across various applications. In some challenging BO tasks, input uncertainty arises due to the inevitable randomness in the optimization process, such as machining errors, execution noise, or contextual variability. This uncertainty deviates the input from the intended value before evaluation, resulting in significant performance fluctuations in the final result. In this paper, we introduce a novel robust Bayesian Optimization algorithm, AIRBO, which can effectively identify a robust optimum that performs consistently well under arbitrary input uncertainty. Our method directly models the uncertain inputs of arbitrary distributions by empowering the Gaussian Process with the Maximum Mean Discrepancy (MMD) and further accelerates the posterior inference via Nystrom approximation. Rigorous theoretical regret bound is established under MMD estimation error and extensive experiments on synthetic functions and real problems demonstrate that our approach can handle various input uncertainties and achieve state-of-the-art performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑