arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.05964cs.PLcs.AIcs.SE
收藏

定量编程实例

Quantitative Programming by Examples

Microsoft Corporation(微软公司)

Sumit Gulwani, Kunal Pathak, Arjun Radhakrishna, Ashish Tiwari, Abhishek Udupa

摘要:

举例编程(Programming-by-Example,PBE)系统从用户提供的少量输入输出示例中,用某种(相对受限的)领域特定语言合成预期的程序。在本文中,我们激励和定义的问题,定量PBE(qPBE),涉及到综合一个潜在的(现实世界)程序设计语言,也最大限度地减少了给定的定量成本函数的预期计划。我们提出了一个模块化的方法来解决qPBE,包括三个阶段:意图消歧,全局搜索和局部搜索。在两个具体的目标,即程序的性能和大小,我们的qPBE程序实现了$1.53 X$和$1.26 X$的改进分别超过基线FlashFill PBE系统,平均超过$701$基准。我们详细的实验验证了我们的程序的设计,并显示了结合全局和局部搜索的qPBE的价值。

英文摘要:

Programming-by-Example (PBE) systems synthesize an intended program in some (relatively constrained) domain-specific language from a small number of input-output examples provided by the user. In this paper, we motivate and define the problem of quantitative PBE (qPBE) that relates to synthesizing an intended program over an underlying (real world) programming language that also minimizes a given quantitative cost function. We present a modular approach for solving qPBE that consists of three phases: intent disambiguation, global search, and local search. On two concrete objectives, namely program performance and size, our qPBE procedure achieves $1.53 X$ and $1.26 X$ improvement respectively over the baseline FlashFill PBE system, averaged over $701$ benchmarks. Our detailed experiments validate the design of our procedure and show the value of combining global and local search for qPBE.

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。

↑