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 2007.00939cs.LGstat.ML
收藏

BOSH:分层抽样贝叶斯优化

BOSH: Bayesian Optimization by Sampling Hierarchically

Lancaster University(兰卡斯特大学)

Henry B. Moss, David S. Leslie, Paul Rayson

摘要:

贝叶斯优化(BO)用于具有随机评估的函数的部署,例如通过交叉验证和仿真优化的参数调整,通常优化目标函数的固定噪声实现集合的平均值。然而,以这种方式忽略真正的目标函数会找到错误函数的高精度最优值。为了解决这个问题,我们提出了贝叶斯优化分层采样(BOSH),一种新的BO例程配对的分层高斯过程与信息理论框架,以生成一个不断增长的实现池的优化进展。我们证明了BOSH在综合基准测试、仿真优化、强化学习和超参数调整任务中提供了比标准BO更高效、更高精度的优化。

英文摘要:

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.

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。

↑