Bibliography
Research Report
LP relaxations and pruning for characteristic imsets
: ÚTIA AVČR, (Praha 2012)
: Research Report 2323
: GA201/08/0539, GA ČR
: learning Bayesian network structure, quality criterion, integer linear programming
(eng): The geometric approach to learning BN structure is to represent it by a certain vector; a suitable such zero-one vector is the characteristic imset, which allows to reformulate the task of finding global maximum of a score over BN structures as an integer linear programming problem. The main contribution of this report is an LP relaxation of the corresponding polytope, that is, a polyhedral description of the domain of the respective integer linear programming problem.
: BA