论文标题
关系程序综合与数值推理
Relational program synthesis with numerical reasoning
论文作者
论文摘要
程序综合方法难以学习数值价值观。一个特别困难的问题是在多个示例（例如间隔）上学习连续值。为了克服这一限制，我们引入了一种归纳逻辑编程方法，该方法将关系学习与数值推理相结合。我们称之为Numsynth的方法使用可满足的模型理论求解器来有效地学习具有数值值的程序。我们的方法可以在线性算术片段中识别数值，例如实际差异逻辑，以及从无限域（例如实数或整数）中的数值。我们对四个不同领域的实验，包括游戏玩法和程序合成，表明我们的方法可以（i）从线性算术推理中学习具有数值值的程序，以及（ii）在预测精度和学习时间方面优于现有方法。
Program synthesis approaches struggle to learn programs with numerical values. An especially difficult problem is learning continuous values over multiple examples, such as intervals. To overcome this limitation, we introduce an inductive logic programming approach which combines relational learning with numerical reasoning. Our approach, which we call NUMSYNTH, uses satisfiability modulo theories solvers to efficiently learn programs with numerical values. Our approach can identify numerical values in linear arithmetic fragments, such as real difference logic, and from infinite domains, such as real numbers or integers. Our experiments on four diverse domains, including game playing and program synthesis, show that our approach can (i) learn programs with numerical values from linear arithmetical reasoning, and (ii) outperform existing approaches in terms of predictive accuracies and learning times.
