Table constraints are very 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 an efficient algorithm for table constraints that achieves a stronger local consistency than GAC. This algorithm, called maxRPWC+, is based on the local consistency maxRPWC and allows the efficient handling of intersecting table constraints. Experimental results from benchmark problems demonstrate that maxRPWC+ is clearly more robust than a state-of-the-art GAC algorithm in classes of problems with interleaved table constraints, being orders of magnitude faster in some of these classes.

The Upper Confidence Bounds (UCB) algorithm is a well-known near-optimal strategy for the stochastic multi-armed bandit problem. Its extensions to trees, such as the Upper Confidence Tree (UCT) algorithm, have resulted in good solutions to the problem of Go. This paper introduces DUCT, a distributed algorithm inspired by UCT, for solving Distributed Constraint Optimization Problems (DCOP). Bounds on the solution quality are provided, and experiments show that, compared to existing DCOP approaches, DUCT is able to solve very large problems much more efficiently, or to find significantly higher quality solutions.

Recently a logic programming language AC was proposed by Mellarkod et al. (2008) to integrate answer set programming (ASP) and constraint logic programming. Similarly, Gebser et al. (2009) proposed a CLINGCON language integrating ASP and finite domain constraints. These languages allow new efficient inference algorithms that combine traditional ASP procedures and other methods in constraint programming. In this paper we show that a transition system introduced by Nieuwenhuis et al. (2006) to model SAT solvers can be extended to model the "hybrid" Acsolver algorithm by Mellarkod et al. developed for simple AC programs and the Clingcon algorithm by Gebser et al. for clingcon programs. We define weakly-simple programs and show how the introduced transition systems generalize the Acsolver and Clingcon algorithms to such programs. Finally, we state the precise relation between AC and CLINGCON languages and the Acsolver and Clingcon algorithms.

Korf, Reid and Edelkamp initiated a line of research for developing methods (KRE and later CDP) that predict the number of nodes expanded by IDA* for a given start state and cost bound. Independent of that, Chen developed a method (SS) that can also be used to predict the number of nodes expanded by IDA*. In this paper we advance both of these prediction methods. First, we develop a variant of CDP that can be orders of magnitude faster than CDP while producing exactly the same predictions. Second, we show how ideas developed in the KRE line of research can be used to substantially improve the predictions produced by SS. Third, we make an empirical comparison between our new enhanced versions of CDP and SS. Our experimental results point out that CDP is suitable for applications that require less accurate but very fast predictions, while SS is suitable for applications that require more accurate predictions but allow more computation time.

In maintaining consistencies, such as GAC*, FDGAC* and weak EDGAC*, for global cost functions, Weighted CSP (WCSP) solvers rely on the projection and extension operations, which entail the computation of the cost functions' minima.  Tractability of this minimum computation is essential for efficient execution. Since projections/extensions modify the cost functions, an important issue is tractable projection-safety , concerning whether minimum cost computation remains tractable after projections/extensions. In this paper, we prove that tractable projection-safety is always possible for projections/extensions to/from the nullary cost function ( W 0 ), and always impossible for projections/extensions to/from n -ary cost functions for n > = 2.  When n = 1, the answer is indefinite.  We give a simple negative example, while Lee and Leung's flow-based projection-safe cost functions are also tractable projection-safe. We propose polynomially decomposable cost functions, which are amenable to tractable minimum computation.  We further prove that the polynomial decomposability property is unaffected by projections/extensionsto/from unary cost functions.  Thus, polynomially decomposable cost functions are tractable projection-safe.  We show that the SOFT_AMONG, SOFT_REGULAR, SOFT_GRAMMAR and MAX_WEIGHT/MIN_WEIGHT are polynomially decomposable.  They are embedded in a WCSP solver for extensive experiments to confirm the feasibility and efficiency of our proposal.

In recent years, significant progress in the area of search, constraint satisfaction, and automated reasoning has been driven in part by the study of challenge problems from combinatorics and finite algebra. This work has led to the discovery of interesting discrete structures with intricate mathematical properties. While some of those results have resolved open questions and conjectures, a shortcoming is that they generally do not provide further mathematical insights, from which one could derive more general observations. We propose an approach that integrates specialized combinatorial search, using so-called streamlining, with a human computation component. We use this approach to discover efficient constructive procedures for generating certain classes of combinatorial objects of any size. More specifically, using our framework, we discovered two complementary efficient constructions for generating so-called Spatially Balanced Latin squares (SBLS) of any order N, such that 2N+1 is prime. Previously constructions for SBLSs were not known. Our approach also enabled us to derive a new lower bound for so-called weak Schur numbers, improving on a series of earlier results for Schur numbers.

Instead, we cluster Search is an integral part of solution approaches for NPhard training instances according to their features and determine combinatorial optimization and decision problems. Once the an assignment of branching heuristics to clusters that results ability to reason deterministically is exhausted, state-of-theart in the best performance when the branching heuristic is dynamically solvers try out different alternatives which may lead to chosen based on the current subproblem's nearest an improved (in case of optimization) or feasible (in case cluster. We test our approach on the MIP-solver Cplex that of satisfaction) solution. This consideration of alternatives we use to tackle set partitioning problems. Our experiments may take place highly opportunistically as in local search approaches, show that this approach can effectively boost search performance or systematically as in backtracking-based methods.

Local Search is one of the fundamental approaches to combinatorial optimization and it is used throughout AI. Several local search algorithms are based on searching the k -exchange neighborhood. This is the set of solutions that can be obtained from the current solution by exchanging at most k elements. As a rule of thumb, the larger k is, the better are the chances of finding an improved solution. However, for inputs of size n, a naive brute-force search of the k-exchange neighborhood requires n (O( k )) time, which is not practical even for very small values of k. Fellows et al. (IJCAI 2009) studied whether this brute-force search is avoidable and gave positive and negative answers for several combinatorial problems. They used the notion of local search in a strict sense. That is, an improved solution needs to be found in the k-exchange neighborhood even if a global optimum can be found efficiently. In this paper we consider a natural relaxation of local search, called permissive local search (Marx and Schlotter, IWPEC 2009) and investigate whether it enhances the domain of tractable inputs. We exemplify this approach on a fundamental combinatorial problem, Vertex Cover. More precisely, we show that for a class of inputs, finding an optimum is hard, strict local search is hard, but permissive local search is tractable. We carry out this investigation in the framework of parameterized complexity.

The increasing availability of “utility computing” resources such as clouds, grids, and massively parallel shared clusters can provide practically unlimited processing and memory capacity on demand, at some cost per unit of resource usage. This requires a new perspective in the design and evaluation of parallel search algorithms. Previous work in parallel search implicitly assumed ownership of a cluster with a static amount of CPU cores and RAM, and emphasized wallclock runtime. With utility computing resources, trade-offs between performance and monetary costs must be considered. This paper considers dynamically increasing the usage of utility computing resources until a problem is solved. Efficient resource allocation policies are analyzed in comparison with an optimal allocation strategy. We evaluate our iterative allocation strategy by applying it to the HDA* parallel search algorithm. The experimental results validate our theoretical predictions. They show that, in practice, the costs incurred by iterative allocation are reasonably close to an optimal (but a priori unknown) policy, and are significantly better than the worst-case analytical bounds.

A* is often described as being `optimal', in that it expands the minimum number of unique nodes. But, A* may generate many extra nodes which are never expanded. This is a performance loss, especially when the branching factor is large. Partial Expansion A* addresses this problem when expanding a node, n, by generating all the children of n but only storing children with the same f-cost as n. n is re-inserted into the OPEN list, but with the f-cost of the next best child. This paper introduces an enhanced version of PEA* (EPEA*). Given a priori domain knowledge, EPEA* generates only the children with the same f-cost as the parent. EPEA* is generalized to its iterative-deepening variant, EPE-IDA*. For some domains, these algorithms yield substantial performance improvements. State-of-the-art results were obtained for the pancake puzzle and for some multi-agent pathfinding instances. Drawbacks of EPEA* are also discussed.