用量子计算中的参数移位法优化黑箱函数，减少查询次数。
Optimization on black-box function by parameter-shift rule
- 引入量子计算的参数移位规则进行零阶优化
- 相比以往方法，所需参数更少，降低查询成本
- 适合参数量大、查询代价高的黑箱优化场景
机器学习已广泛应用于多个领域，但训练模型的难度日益增加。许多优化问题属于“黑箱”类型，其模型参数与结果之间的关系不确定或难以追踪。当前针对需大量查询观测和参数的黑箱模型优化方法面临困难。为克服现有算法的局限，本研究提出一种源自量子计算的零阶优化方法——参数移位规则，该方法所需参数数量少于以往方法，显著降低了优化过程中的查询需求。
原文摘要 · Abstract (English)
Machine learning has been widely applied in many aspects, but training a machine learning model is increasingly difficult. There are more optimization problems named "black-box" where the relationship between model parameters and outcomes is uncertain or complex to trace. Currently, optimizing black-box models that need a large number of query observations and parameters becomes difficult. To overcome the drawbacks of the existing algorithms, in this study, we propose a zeroth-order method that originally came from quantum computing called the parameter-shift rule, which has used a lesser number of parameters than previous methods.
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。