Improving Constraint Satisfaction Algorithm Efficiency for the AllDifferent Constraint
Abstract
Combinatorial problems stated as Constraint Satisfaction Problems (CSP) are examined. It is shown by example that any algorithm designed for the original CSP, and involving the AllDifferent constraint, has at least the same level of efficacy when simultaneously applied to both the original and its complementary problem. The 1-to-1 mapping employed to transform a CSP to its complementary problem, which is also a CSP, is introduced. This "Dual CSP" method and its application are outlined. The analysis of several random problem instances demonstrate the benefits of this method for variable domain reduction compared to the standard approach to CSP. Extensions to additional constraints other than AllDifferent, as well as the use of hybrid algorithms, are proposed as candidates for this Dual CSP method.
Cite
@article{arxiv.2012.03624,
title = {Improving Constraint Satisfaction Algorithm Efficiency for the AllDifferent Constraint},
author = {Geoff Harris},
journal= {arXiv preprint arXiv:2012.03624},
year = {2020}
}
Comments
*sigh* - it has been gently and kindly pointed out to me that I have simply re-discovered the channelling of constraints across alternate problem specifications. Gosh this is oddly amusing albeit embarrassing!