Tag
提出了 ELF-BO 算法，利用目标函数评估的等待时间提前从超参数后验中采样，仅在观测到目标值后重新加权，从而以标准 BO 的决策延迟实现完全贝叶斯优化。在合成函数和真实应用中，ELF-BO 匹配完全贝叶斯方法的性能且延迟更低。
This paper addresses the challenge of generating normative rules that are both human-readable and operationally verifiable, introducing GNRS-Search with MCMC sampling and evaluating it on benchmarks for improved rule quality.