优化简单表缩减算法求解因子分解编码实例

表约束在约束程序（constraint programming,简称CP）中被广泛研究.目前,求解表约束问题效率最高的算法是CT （compact-table）和STRbit （simple tabular reduction bit）.它们在搜索过程中维持广义弧相容（generalized arc consistency,简称GAC）.完全成对相容（full pairwise consistency,简称fPWC）是一种强于GAC的相容性关系,目前,实现fPWC效率最高的算法是PW-CT,但是它无法直接在通用的求解器上实现.因子分解编码（factor-decomposition encoding,简称FDE）是实现fPWC的一种编码方式,通常和简单表缩减（STR）算法一起来使用.当前效率最高的STR算法使用了bitset的数据结构,用这些算法来求解FDE实例可能会造成内存溢出.提出了STRFDE算法——一种使用bitset结构来求解FDE实例的方法.它结合了CT和STRbit的优势,在保证求解效率的同时,使占用的内存尽可能小.实验结果表明,在许多存在非平凡相交的实例上,该算法是有竞争力的.     

一种高效的FDE并行传播算法

约束规划(constraint programming, CP)是表示和求解组合问题的经典范式之一.扩展约束(extensional constraint)或称表约束(table constraint)是约束规划中最为常见的约束类型.绝大多数约束规划问题都可以用表约束表达.在问题求解时,相容性算法用于缩减搜索空间.目前,最为高效的表约束相容性算法是简单表约缩减(simple table reduction, STR)算法簇,如Compact-Table (CT)和STRbit算法.它们在搜索过程中维持广义弧相容(generalized arc consistency, GAC).此外,完全成对相容性(full pairwise consistency, fPWC)是一种比GAC剪枝能力更强的相容性.最为高效的维持fPWC算法是PW-CT算法.多年来,人们提出了多种表约束相容性算法来提高剪枝能力和执行效率.因子分解编码(factor-decomposition encoding, FDE)通过对平凡问题重新编码.它一定程度地扩大了问题模型,使在新的问题上维持相对较弱的GAC等价于在原问题...     

一种基于时间戳的简单表缩减算法

表约束是一种外延的知识表示方法,每个约束在对应的变量集上列举出所有支持或禁止的元组.广义弧相容（generalized arc consistency,简称GAC）是求解约束满足问题应用最广泛的相容性.Simple Tabular Reduction（STR）是一类高效的维持GAC的算法.在回溯搜索中,STR动态地删除无效元组,降低了查找支持的开销,并拥有单位时间的回溯代价,在高元表约束上获得了广泛运用,并有大量基于STR的改进算法被提出,其中,元组集的压缩表示是目前研究较多的方法.同样基于动态维持元组集有效部分的思想,为STR提出一种检测并删除无效元组和为变量更新支持的算法,作用于原始表约束并拥有单位时间的回溯代价.实验结果表明,该算法在表约束上维持GAC的效率普遍高于现有的非基于压缩表示的STR算法,并且在一些实例上的效率高于最新的基于元组集压缩表示的STR算法.     

基于多核CPU的表约束并行传播模式研究

并行传播是并行约束程序领域中的一个研究方向,其研究内容是如何并行执行在约束上的过滤算法.根据维持表约束网络广义弧相容（generalized arc consistency,简称GAC）的串行传播模式,提出了维持表约束网络临时广义弧相容（temporary generalized arc consistency,简称TGAC）的并行传播模式,该模式基于多核CPU,由并行传播算法和并行过滤算法两部分组成;之后,给出了并行传播模式的可靠性证明,而且通过对并行传播模式的最坏时间复杂度分析,可以认为并行传播模式在平均过滤时间较长的实例上要快于串行传播模式;最终的实验结果也验证了上述结论,并行传播模式在多数实例集上取得了从1.4~3.4不等的加速比.     

自适应表压缩方法优化STR算法

表约束,也称为外延式约束,是约束编程领域最常见的约束形式,表压缩方法通过紧凑的表示元组集可以极大地缩减空间消耗,同时加速 GAC 算法。笛卡尔乘积表示和短支持是表约束中最常见的两种表压缩方法,两种表压缩方法在同一问题上的压缩率是影响它们优化效果的主要原因。基于 STR 算法提出一种自适应表压缩方法,在求解问题时自适应选择压缩率大的表压缩方法,将自适应表压缩方法应用到 STR2 上提出了 STR2 Adaptive 算法,可以同时覆盖两种表压缩方法的优势。实验结果表明,STR2 Adaptive 算法在绝大部分实例上都能自适应选择最佳的表压缩方法,有效地减少了STR2算法空间消耗和CPU运行时间。然后将自适应表压缩方法扩展到采用了高效的比特向量表示的 STRbit 算法上提出了 STRbit Adaptive 算法。实验结果表明,STRbit Adaptive 算法效率同样普遍优于 STRbit 算法。     

概率最大受限路径相容算法

研究了可用于求解约束满足问题的最大受限路径相容算法(maxRPC).maxRPC算法执行过程中有大量无效的寻找路径相容证明(PC-witness)的操作,有效地识别和避免这些无效的寻找PC-witness的操作,可以提高maxRPC算法的求解效率.首先,提出了在一条约束上任意两个相容的值在任意路径上存在PC-witness的概率;然后,基于这一概率提出了一种概率最大受限路径相容算法(PmaxRPC),并将新算法成功应用于求解约束满足问题的回溯搜索.实验结果显示:PmaxRPC可以避免一部分无效的寻找PC-witness的操作,在求解约束满足问题时,PmaxRPC效率高于maxRPC.在某些测试用例上,PmaxRPC比maxRPC和最流行的弧相容算法效率更高.     

改进求解约束满足问题粗粒度弧相容算法

约束满足问题在人工智能领域有着广泛的应用.研究了约束满足问题的粗粒度维持弧相容求解算法,发现在求解过程中,对于指向已赋值变量的弧存在无效的修正检查,证明了这类修正检查是冗余的.提出一种方法避免这类冗余的修正检查,给出改进后的粗粒度弧相容算法的基本框架AC3_frame_ARR,该改进框架可用于改进所有粗粒度弧相容算法.实验结果表明,经过AC3_frame_ARR改进后的算法最多可以节省80%的修正检查次数和40%的求解耗时.     

Improving Coarse-Grained Arc Consistency Algorithms in Solving Constraint Satisfaction Problems

约束满足问题在人工智能领域有着广泛的应用.研究了约束满足问题的粗粒度维持弧相容求解算法,发现在求解过程中,对于指向已赋值变量的弧存在无效的修正检查,证明了这类修正检查是冗余的.提出一种方法避免这类冗余的修正检查,给出改进后的粗粒度弧相容算法的基本框架AC3_frame_ARR,该改进框架可用于改进所有粗粒度弧相容算法.实验结果表明,经过AC3 frame ARR改进后的算法最多可以节省80％的修正检查次数和40％的求解耗时.     

优化求解约束满足问题的MDDc和STR3算法

广义弧相容是求解约束满足问题应用最广泛的相容性,MDDc、STR2和STR3是表约束上维持广义弧相容应用较多的算法,其中MDDc基于对约束压缩表示的思想,将表约束表示成多元决策图,对各个元组之间存在较多交叠部分的约束具有很好的压缩效果;STR3同STR2一样基于动态维持有效元组的思想,当元组集规模缩减较慢时STR3维持广义弧相容的效率高于STR2.通过深入分析发现MDDc中查找节点的有效出边和STR3中检测并删除无效元组是耗时最多的操作.本文分别对MDDc和STR3提出一种自适应查找有效出边和检测删除无效元组的方法AdaptiveMDDc和AdaptiveSTR,对于同一操作,可以根据回溯搜索不同阶段的局势自适应地选择代价最小的实现方法,得益于较低的判断代价以及回溯搜索不同阶段采用不同方法的效率差异,AdaptiveMDDc和AdaptiveSTR相比原算法速度提升显著,其中AdaptiveSTR在一些问题上相比STR3提速三倍以上.     

最先失败原则的约束传播算法

约束满足问题是人工智能研究领域的重要问题.而弧相容算法是求解约束满足问题的重要工具.在弧相容算法中应用启发式规则已经证明是一种很有效的方式.本文提出一个基于最先失败原则的约束传播算法,该算法在搜索过程中更早地发现含有空域的变量并提前进行回溯,从而提高问题求解效率.同时,在"明月1.0"架构下实现了该算法,实验结果表明使用最先失败原则的弧相容算法要比原来的算法效率上提高了约40%.     

Strong local consistency algorithms for table constraints

Table constraints are important in constraint programming as they are present in many real problems from areas such as configuration and databases. As a result, numerous specialized algorithms that achieve generalized arc consistency (GAC) on table constraints have been proposed. Since these algorithms achieve GAC, they operate on one constraint at a time. In this paper we propose new filtering algorithms for positive table constraints that achieve stronger local consistency properties than GAC by exploiting intersections between constraints. The first algorithm, called maxRPWC+, is a domain filtering algorithm that is based on the local consistency maxRPWC and extends the GAC algorithm of Lecoutre and Szymanek (2006). The second algorithm extends the state-of-the-art STR-based algorithms to stronger relation filtering consistencies, i.e., consistencies that can remove tuples from constraints’ relations. Experimental results from benchmark problems demonstrate that the proposed algorithms are quite competitive with standard GAC algorithms like STR2 in some classes of problems with intersecting table constraints, being orders of magnitude faster in some cases.     

STR2: optimized simple tabular reduction for table constraints

Table constraints play an important role within constraint programming. Recently, many schemes or algorithms have been proposed to propagate table constraints and/or to compress their representation. In this paper, we describe an optimization of simple tabular reduction (STR), a technique proposed by J. Ullmann to dynamically maintain the tables of supports when generalized arc consistency (GAC) is enforced/maintained. STR2, the new refined GAC algorithm we propose, allows us to limit the number of operations related to validity checking and search of supports. Interestingly enough, this optimization makes simple tabular reduction potentially r times faster where r is the arity of the constraint(s). The results of an extensive experimentation that we have conducted with respect to random and structured instances indicate that STR2 is usually around twice as fast as the original STR, two or three times faster than the approach based on the hidden variable encoding, and can be up to one order of magnitude faster than previously state-of-the-art (generic) GAC algorithms on some series of instances. When comparing STR2 with the more recently developed algorithm based on multi-valued decision diagrams (MDDs), we show that both approaches are rather complementary.     

The extended global cardinality constraint: An empirical survey

The Extended Global Cardinality Constraint (EGCC) is a vital component of constraint solving systems, since it is very widely used to model diverse problems. The literature contains many different versions of this constraint, which trade strength of inference against computational cost. In this paper, I focus on the highest strength of inference usually considered, enforcing generalized arc consistency (GAC) on the target variables. This work is an extensive empirical survey of algorithms and optimizations, considering both GAC on the target variables, and tightening the bounds of the cardinality variables. I evaluate a number of key techniques from the literature, and report important implementation details of those techniques, which have often not been described in published papers. Two new optimizations are proposed for EGCC. One of the novel optimizations (dynamic partitioning, generalized from AllDifferent) was found to speed up search by 5.6 times in the best case and 1.56 times on average, while exploring the same search tree. The empirical work represents by far the most extensive set of experiments on variants of algorithms for EGCC. Overall, the best combination of optimizations gives a mean speedup of 4.11 times compared to the same implementation without the optimizations.     

Optimal and efficient filtering algorithms for table constraints

Filtering algorithms for table constraints can be classified in two categories: constraint-based and value-based. In the constraint-based approaches, the propagation queue only contains information on the constraints that must be reconsidered. For the value-based approaches, the propagation queue also contains information on the removed values. This paper proposes five efficient value-based algorithms for table constraints. Two of them (AC5TCOpt-Tr and AC5TCOpt-Sparse) are proved to have an optimal time complexity of O(r·t+r·d) per table constraint. Substantial experimental results are presented. An empirical analysis is conducted on the effect of the arity of the tables. The experiments show that our propagators are the best when the arity of the table is 3 or 4. Indeed, on instances containing only binary constraints, our algorithms are outperformed by classical AC algorithm AC3rm. AC3rm is dedicated to binary constraints. However, all our algorithms outperform existing state-of-the-art constraint based STR2+ and MDD ^c and the optimal value-based STR3 algorithms on those instances. On instances with small arity tables (up to arity 4), all our algorithms are generally faster than STR2+, MDD ^c and than STR3. AC5TCOpt-Sparse is globally the best propagator on those benchmarks. On benchmarks containing large arity tables (arity 5 or more), each of the three existing state-of-the-art algorithms is the winning strategy on one different benchmark.