arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.08663cs.PL
收藏

自底向上的枚举综合的即时学习

Just-in-Time Learning for Bottom-Up Enumerative Synthesis

Shraddha Barke, Hila Peleg, Nadia Polikarpova

摘要:

程序合成中的一个关键挑战是合成器必须探索的搜索空间的天文数字大小。为了应对这一挑战,最近的工作提出了使用学习的概率模型来指导合成。然而,对于没有高质量训练数据可用的问题域,获得这样的模型可能是不可行的。在这项工作中,我们介绍了一种替代方法,引导程序合成:而不是提前训练模型,我们展示了如何引导一个只是在时间,在合成过程中,从沿途遇到的部分解决方案的学习。为了充分利用该模型,我们还提出了一个新的程序枚举算法,我们称之为引导自自底向上的【形】的搜索,它扩展了有效的自自底向上的【形】的搜索与概率模型的指导。我们在一个名为Probe的工具中实现了这种方法,该工具针对流行的语法指导合成(SyGuS)格式中的问题。我们从文献中的基准评估探针,并表明,它实现了显着的性能增益,无论是在无指导的自自底向上的【形】的搜索和一个国家的最先进的概率引导合成器,这已经训练了现有的解决方案的语料库。此外,我们表明,这些性能的提高并不以解决方案的质量为代价:由探针产生的程序只是稍微比最短的解决方案更冗长,并没有执行不必要的情况下分裂。

英文摘要:

A key challenge in program synthesis is the astronomical size of the search space the synthesizer has to explore. In response to this challenge, recent work proposed to guide synthesis using learned probabilistic models. Obtaining such a model, however, might be infeasible for a problem domain where no high-quality training data is available. In this work we introduce an alternative approach to guided program synthesis: instead of training a model ahead of time we show how to bootstrap one just in time, during synthesis, by learning from partial solutions encountered along the way. To make the best use of the model, we also propose a new program enumeration algorithm we dub guided bottom-up search, which extends the efficient bottom-up search with guidance from probabilistic models. We implement this approach in a tool called Probe, which targets problems in the popular syntax-guided synthesis (SyGuS) format. We evaluate Probe on benchmarks from the literature and show that it achieves significant performance gains both over unguided bottom-up search and over a state-of-the-art probability-guided synthesizer, which had been trained on a corpus of existing solutions. Moreover, we show that these performance gains do not come at the cost of solution quality: programs generated by Probe are only slightly more verbose than the shortest solutions and perform no unnecessary case-splitting.

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。

↑