用强化学习思路优化函数，兼顾探索与利用，高效找全局最优解。
Bandits attack function optimization
- 基于连续多臂老虎机思想，通过分域搜索平衡探索与利用。
- 在CEC'2014测试集上实现高精度求解，保证收敛性与计算效率。
- 适合需要严格预算约束的黑盒函数优化任务。
我们将函数优化视为在预算约束下的序列决策问题，该约束限制了目标函数评估次数。受连续多臂老虎机启发，提出一种算法，以解决探索（初始均匀域搜索）与利用（围绕潜在全局最大值局部优化）之间的权衡。引入确定性算法Simultaneous Optimistic Optimization（SOO），通过域划分实现优化。该方法具有解的收敛性保证和良好的数值效率。本文介绍这一机器学习优化方法，并在CEC'2014单目标实参数数值优化竞赛测试集上进行了实证评估。
原文摘要 · Abstract (English)
We consider function optimization as a sequential decision making problem under budget constraint. This constraint limits the number of objective function evaluations allowed during the optimization. We consider an algorithm inspired by a continuous version of a multi-armed bandit problem which attacks this optimization problem by solving the tradeoff between exploration (initial quasi-uniform search of the domain) and exploitation (local optimization around the potentially global maxima). We introduce the so-called Simultaneous Optimistic Optimization (SOO), a deterministic algorithm that works by domain partitioning. The benefit of such approach are the guarantees on the returned solution and the numerical efficiency of the algorithm. We present this machine learning approach to optimization, and provide the empirical assessment of SOO on the CEC'2014 competition on single objective real-parameter numerical optimization test-suite.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。