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 2007.04674cs.LGphysics.data-anstat.ML
收藏

资源感知多保真度主动学习的高效优化

Resource Aware Multifidelity Active Learning for Efficient Optimization

United Technologies Research Centre Ireland, Ltd(联合技术研究中心(爱尔兰)有限公司);Gran Sasso Science Institute(格兰索科学研究所);University College Cork(科克大学学院)

Francesco Grassi, Giorgio Manganini, Michele Garraffa, Laura Mainini

摘要:

传统的黑盒优化方法需要大量的评估,这可能是耗时的,不切实际的,并且对于依赖于精确表示和昂贵模型来评估的许多工程应用来说通常是不可行的。贝叶斯优化(BO)方法通过沿着搜索路径渐进地(主动地)学习目标函数的代理模型来搜索全局最优。贝叶斯优化可以通过多保真度方法来加速,该方法利用目标函数的多个黑盒近似,这些黑盒近似可以在计算上更便宜地进行评估,但仍然为搜索任务提供相关信息。并行和分布式计算体系结构的可用性提供了进一步的计算益处,其最佳使用是主动学习背景下的开放机会。本文介绍了资源感知主动学习(RAAL)策略,一个多保真度贝叶斯方案,以加速优化的黑盒功能。在每个优化步骤中,RAAL过程计算最佳样本位置和相关保真度源的集合,其最大化在目标函数的并行/分布式评估期间获取的信息增益,同时考虑有限的计算预算。该计划被证明为各种基准的问题和结果进行了讨论,为单保真度和多保真度设置。特别是我们观察到,RAAL策略在每次迭代时最佳地播种多个点,从而大大加快了优化任务的速度。

英文摘要:

Traditional methods for black box optimization require a considerable number of evaluations which can be time consuming, unpractical, and often unfeasible for many engineering applications that rely on accurate representations and expensive models to evaluate. Bayesian Optimization (BO) methods search for the global optimum by progressively (actively) learning a surrogate model of the objective function along the search path. Bayesian optimization can be accelerated through multifidelity approaches which leverage multiple black-box approximations of the objective functions that can be computationally cheaper to evaluate, but still provide relevant information to the search task. Further computational benefits are offered by the availability of parallel and distributed computing architectures whose optimal usage is an open opportunity within the context of active learning. This paper introduces the Resource Aware Active Learning (RAAL) strategy, a multifidelity Bayesian scheme to accelerate the optimization of black box functions. At each optimization step, the RAAL procedure computes the set of best sample locations and the associated fidelity sources that maximize the information gain to acquire during the parallel/distributed evaluation of the objective function, while accounting for the limited computational budget. The scheme is demonstrated for a variety of benchmark problems and results are discussed for both single fidelity and multifidelity settings. In particular we observe that the RAAL strategy optimally seeds multiple points at each iteration allowing for a major speed up of the optimization task.

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。

↑