按预期改进列出的optimization中的不一致示例
Examples of inconsistency in optimization by expected improvement
摘要:
我们考虑基于高斯过程的一维期望改进优化,其谱密度收敛到零的速度比指数快。我们给出了优化轨迹在设计空间中不密集的问题的例子。特别是,我们证明了高斯核存在光滑的目标函数的优化不收敛于最佳。
英文摘要:
We consider the 1D Expected Improvement optimization based on Gaussian processes having spectral densities converging to zero faster than exponentially. We give examples of problems where the optimization trajectory is not dense in the design space. In particular, we prove that for Gaussian kernels there exist smooth objective functions for which the optimization does not converge on the optimum.
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。