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 1607.04817math.OCcs.AI
收藏

具有误差界和快速收敛性的全局连续Optimization

Global Continuous Optimization with Error Bound and Fast Convergence

Massachusetts Institute of Technology(麻省理工学院);Japan Atomic Energy Agency(日本原子能研究开发机构)

Kenji Kawaguchi, Yu Maruyama, Xiaoyu Zheng

摘要:

本文研究了具有非凸不可微的黑箱未知目标函数的全局优化问题。这样一个困难的最优化问题出现在许多现实世界的应用中,如机器学习中的参数调整,工程设计问题,和规划与复杂的物理模拟器。本文提出了一种新的全局优化算法,称为局部导向全局优化算法(Locally Oriented Global Optimization,简称LOO),以实现快速收敛和有限时间误差界为目标。通过理论分析和对11个基准检验函数的实验,说明了新算法的优点和使用方法。此外,我们修改的策略搜索算法,专门解决规划问题,通过连续的状态/动作空间和长的时间范围,同时保持其有限的时间误差界。我们提出的规划方法,核电厂的事故管理。应用研究的结果表明,我们的方法的实际效用。

英文摘要:

This paper considers global optimization with a black-box unknown objective function that can be non-convex and non-differentiable. Such a difficult optimization problem arises in many real-world applications, such as parameter tuning in machine learning, engineering design problem, and planning with a complex physics simulator. This paper proposes a new global optimization algorithm, called Locally Oriented Global Optimization (LOGO), to aim for both fast convergence in practice and finite-time error bound in theory. The advantage and usage of the new algorithm are illustrated via theoretical analysis and an experiment conducted with 11 benchmark test functions. Further, we modify the LOGO algorithm to specifically solve a planning problem via policy search with continuous state/action space and long time horizon while maintaining its finite-time error bound. We apply the proposed planning method to accident management of a nuclear power plant. The result of the application study demonstrates the practical utility of our method.

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。

↑