LambdaBeam:基于高阶函数与Lambda的神经程序搜索
LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdas
AI总结:
LambdaBeam通过神经策略网络构造lambda函数并传递给高阶函数实现循环计算,解决了神经程序搜索无法处理高阶函数和lambda的问题,在整数列表操作领域优于神经、符号和LLM方法。
摘要:
搜索是程序合成中的一项重要技术,它允许根据执行结果采用自适应策略,例如聚焦于特定搜索方向。多项先前工作已经证明神经模型能够有效引导程序合成搜索。然而,这些方法的一个共同缺陷是无法处理迭代循环、高阶函数或lambda函数,从而限制了先前神经搜索方法合成更长、更通用程序的能力。我们通过设计一种名为LambdaBeam的搜索算法来弥补这一不足,该算法能够构造任意lambda函数,用于组合给定DSL中的操作。我们为lambda函数的执行行为创建语义向量表示,并训练一个神经策略网络,在搜索过程中选择要构造哪些lambda,并将它们作为参数传递给高阶函数以执行循环计算。我们的实验表明,在整数列表操作领域中,LambdaBeam优于基于神经、符号和LLM的技术。
英文摘要:
Search is an important technique in program synthesis that allows for adaptive strategies such as focusing on particular search directions based on execution results. Several prior works have demonstrated that neural models are effective at guiding program synthesis searches. However, a common drawback of those approaches is the inability to handle iterative loops, higher-order functions, or lambda functions, thus limiting prior neural searches from synthesizing longer and more general programs. We address this gap by designing a search algorithm called LambdaBeam that can construct arbitrary lambda functions that compose operations within a given DSL. We create semantic vector representations of the execution behavior of the lambda functions and train a neural policy network to choose which lambdas to construct during search, and pass them as arguments to higher-order functions to perform looping computations. Our experiments show that LambdaBeam outperforms neural, symbolic, and LLM-based techniques in an integer list manipulation domain.
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。