高斯过程内核表达的死亡率模型（英文版）

英文标题：Expressive Mortality Models through Gaussian Process Kernels中文摘要：本文利用柔性高斯过程框架，设计了遗传编程算法来搜索适合于特定人口的最具表现性的内核。研究旨在揭示不同人口中队列效应有无及死亡率表面在年龄和年份维度上的相对平滑性。用编程算法对全国范围的真实数据集进行验证。英文摘要：We develop a flexible Gaussian Process (GP) framework for learning thecovariance structure of Age- and Year-specific mortality surfaces. Utilizingthe additive and multiplicative structure of GP kernels, we design a geneticprogramming algorithm to search for the most expressive kernel for a givenpopulation. Our composition