基于SVM的多项式循环程序秩函数生成  

SVM-based Method for Detecting Ranking Functions in Polynomial Loop Programs

作　　者：李轶[1] 蔡天训 樊建峰 吴文渊[1] 冯勇[1] LI Yi;CAI Tian-Xun;FAN Jian-Feng;WU Wen-Yuan;FENG Yong(Chongqing Key Laboratory of Automated Reasoning and Cognition, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing 400714, China;Sagemcom Technologies Inc., Shenzhen 518000, China;School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing 100093, China)

机构地区：[1]中国科学院重庆绿色智能技术研究院自动推理与认知重庆市重点实验室,重庆400714 [2]萨基姆通讯(深圳)有限公司,广东深圳518000 [3]中国科学院大学计算机科学与技术学院,北京100093

出　　处：《软件学报》2019年第7期1903-1915,共13页Journal of Software

基　　金：国家自然科学基金(61572024,61103110,11471307)~~

摘　　要：程序终止性问题是自动程序验证领域中的一个研究热点。秩函数探测是进行终止性分析的主要方法。针对单重无条件分支的多项式循环程序,将其秩函数计算问题归结为二分类问题,从而可利用支持向量机(SVM)算法来计算程序的秩函数。与基于量词消去技术的秩函数计算方法不同,该方法能在可接受的时间范围内探测到更为复杂的秩函数。Synthesizing ranking functions of polynomial loop programs is the dominant method for checking their termination.In this study,the synthesis of ranking functions of a class of polynomial loop program is reduced to the binary problem.The support vector machine(SVM)technique then is applied to solve such the binary problem.This naturally relates detection of ranking functions to SVM.Different from the CAD-based method for synthesizing ranking functions,the proposed method can get more expressive polynomial ranking functions in an acceptable time.

关 键 词：程序终止性 SVM 机器学习 秩函数 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]