论文标题
BOSH：通过层次进行采样来优化贝叶斯
BOSH: Bayesian Optimization by Sampling Hierarchically
论文作者
论文摘要
贝叶斯优化（BO）的部署用于具有随机评估的功能，例如通过交叉验证和仿真优化进行参数调整，通常优化了一组固定的目标函数噪声实现的平均值。但是，以这种方式忽略真实的目标函数可以找到错误的函数的高精度最佳。为了解决这个问题，我们提出了通过层次（bosh）取样的贝叶斯优化，这是一种新颖的bo例程将层次高斯过程与信息理论框架配对，以随着优化的进行而产生越来越多的实现池。我们证明，BOSH比跨合成基准，模拟优化，强化学习和超参数调整任务提供了比标准BO更有效，更高的优化。
Deployments of Bayesian Optimization (BO) for functions with stochastic evaluations, such as parameter tuning via cross validation and simulation optimization, typically optimize an average of a fixed set of noisy realizations of the objective function. However, disregarding the true objective function in this manner finds a high-precision optimum of the wrong function. To solve this problem, we propose Bayesian Optimization by Sampling Hierarchically (BOSH), a novel BO routine pairing a hierarchical Gaussian process with an information-theoretic framework to generate a growing pool of realizations as the optimization progresses. We demonstrate that BOSH provides more efficient and higher-precision optimization than standard BO across synthetic benchmarks, simulation optimization, reinforcement learning and hyper-parameter tuning tasks.
