Scalable Bayesian Optimization with Memory Retention
Scalable Bayesian Optimization with Memory Retention
复制标题
具有内存保留的可扩展贝叶斯优化
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Hidetaka Ito
中科院分区：
文献类型：
--
作者：
Hidetaka Ito
贝叶斯优化是一种对黑盒函数进行全局优化的方法，其求值次数尽可能少。它利用高斯过程来有效地选择要评估的参数。然而，它是不可伸缩的，因为高斯过程随着迭代次数的立方缩放。在这项工作中，我们提出了一种可扩展的贝叶斯优化方法，利用模型在过去的迭代，我们称之为过去的记忆。这种技术使我们能够适应高斯过程，只有输入输出对附近的先前选定的输入参数。在实验中，我们表明我们提出的方法优于朴素贝叶斯优化的优化性能有限的时间预算。
Bayesian optimization is a method for the global optimization of black-box functions as few evaluation as possible. It utilizes Gaussian processes to efficiently select parameters to be evaluated. However, it is not scalable because Gaussian processes scale cubically with the number of iterations. In this work, we propose a method for scalable Bayesian optimization by leveraging models used in past iterations, which we call past memory. This technique enables us to fit Gaussian processes to only input-output pairs near the previously selected input parameter. In experiments, we show our proposed method outperforms naive Bayesian optimization in terms of optimization performance with limited time budget.