2021/03/24 by Verma, Amit, Lewis, Mark
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Mathematics #Optimization and Control (math.OC)
paper · doi:10.48550/arxiv.2103.12951
The Quadratic Unconstrained Binary Optimization (QUBO) modeling and solution framework is a requirement for quantum and digital annealers. However optimality for QUBO problems of any practical size is extremely difficult to achieve. In order to incorporate the problem-specific insights, a diverse set of solutions meeting an acceptable target metric or goal is the preference in high level decision making. In this paper, we present two alternatives for goal-seeking QUBO for minimizing the deviation from a given target as well as a range of values around a target. Experimental results illustrate the efficacy of the proposed approach over Constraint Programming for quickly finding a satisficing set of solutions.