Optimizing Dynamic Structures with Bayesian Generative Search
Optimizing Dynamic Structures with Bayesian Generative Search
复制标题
DOI：
--
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Minh Hoang;Carleton Kingsford
中科院分区：
文献类型：
--
作者：
Minh Hoang;Carleton Kingsford
由于离散优化的NP难性质，基于核的方法的核选择是极其昂贵的。由于基于梯度的优化器由于缺乏可微目标函数而不适用，因此许多最先进的解决方案求助于启发式搜索或无梯度优化。然而，这些方法需要对结构的可探索空间施加限制性假设，例如限制活动候选池，从而严重依赖于领域专家的直觉。相反，本文提出了DTERGENS，一种新的生成搜索框架，构建和优化了一个高性能的复合内核表达式生成器。DTERGENS不限制候选核的空间，并且能够通过联合优化生成终止准则来获得可扩展的长度表达式。我们证明了我们的框架探索了更多样化的内核，并在许多现实世界的预测任务上获得了比最先进的方法更好的性能。
Kernel selection for kernel-based methods is pro-hibitively expensive due to the NP-hard nature of discrete optimization. Since gradient-based optimizers are not applicable due to the lack of a differentiable objective function, many state-of-the-art solutions resort to heuristic search or gradient-free optimization. These approaches, however, require imposing restrictive assumptions on the explorable space of structures such as limiting the active candidate pool, thus depending heavily on the intuition of domain experts. This paper instead proposes DTERGENS , a novel generative search framework that constructs and optimizes a high-performance composite kernel expressions generator. DTERGENS does not restrict the space of candidate kernels and is capable of obtaining flexi-ble length expressions by jointly optimizing a generative termination criterion. We demonstrate that our framework explores more diverse kernels and obtains better performance than state-of-the-art approaches on many real-world predictive tasks.