Today I read a paper titled “Postponing Branching Decisions”
The abstract is:
Solution techniques for Constraint Satisfaction and Optimisation Problems often make use of backtrack search methods, exploiting variable and value ordering heuristics.
In this paper, we propose and analyse a very simple method to apply in case the value ordering heuristic produces ties: postponing the branching decision.
To this end, we group together values in a tie, branch on this sub-domain, and defer the decision among them to lower levels of the search tree.
We show theoretically and experimentally that this simple modification can dramatically improve the efficiency of the search strategy.
Although in practise similar methods may have been applied already, to our knowledge, no empirical or theoretical study has been proposed in the literature to identify when and to what extent this strategy should be used.