arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.09182cs.LG
收藏

将领域知识转化为神经引导搜索

Incorporating domain knowledge into neural-guided search

Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室)

Brenden K. Petersen, Claudio P. Santiago, Mikel Landajuela

摘要:

许多AutoML问题涉及在黑盒奖励下优化离散对象。神经引导搜索提供了一种灵活的方法,使用自回归递归神经网络搜索这些组合空间。这种方法的一个主要好处是顺序构建对象--这提供了一个通过直接修改采样期间发出的logit将领域知识纳入搜索的机会。在这项工作中,我们正式的框架,将这种在原位的先验和约束神经引导搜索,并提供充分的条件,强制执行的约束。我们整合了现有的工作到这个框架中的先验和约束,提出了几个新的,并证明了它们的有效性,通知任务的象征性回归。

英文摘要:

Many AutoML problems involve optimizing discrete objects under a black-box reward. Neural-guided search provides a flexible means of searching these combinatorial spaces using an autoregressive recurrent neural network. A major benefit of this approach is that builds up objects sequentially--this provides an opportunity to incorporate domain knowledge into the search by directly modifying the logits emitted during sampling. In this work, we formalize a framework for incorporating such in situ priors and constraints into neural-guided search, and provide sufficient conditions for enforcing constraints. We integrate several priors and constraints from existing works into this framework, propose several new ones, and demonstrate their efficacy in informing the task of symbolic regression.

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。

↑