Correlation Heuristics for Constraint Programming

Effective general-purpose search strategies are an important component in Constraint Programming. We introduce a new idea, namely, using correlations between variables to guide search. Variable correlations are measured and maintained by using domain changes during constraint propagation. We propose two variable heuristics based on the correlation matrix, crbs-sum and crbs-max. We evaluate our correlation heuristics with well known heuristics, namely, domiwdeg, impact-based search and activity-based search. Experiments on a large set of benchmarks show that our correlation heuristics are competitive with the other heuristics, and can be the fastest on many series.