The Quadratic Unconstrained Binary Optimization (QUBO) modeling and solution framework is required for quantum and digital annealers whose goal is the optimization of a well defined metric, the objective function. However, diverse suboptimal solutions may be preferred over harder to implement strict optimal ones. In addition, the decision-maker usually has insights that are not always efficiently translated into the optimization model, such as acceptable target, interval or range values. Multi-criteria decision making is an example of involving the user in the decision process. In this paper, we present two variants of goal-seeking QUBO that minimize the deviation from the goal through a tabu-search based greedy one-flip heuristic. Experimental results illustrate the efficacy of the proposed approach over Constraint Programming for quickly finding a satisficing set of solutions.
翻译：对于量子和数字肛交者,其目标在于优化一个定义明确的计量标准,即目标功能,需要采用“无限制的二进制优化”模型和解决方案框架。然而,对于严格的最佳衡量标准,可能更倾向于采用不同的次优解决方案,而不是更难地实施。此外,决策者通常具有并非总能有效转化为优化模式的洞察力,例如可接受的目标、间隔或范围值。多标准决策是让用户参与决策过程的一个实例。在本文件中,我们介绍了两个寻求目标的QUBO变种,它们通过基于 Tabu-searing的贪婪一翻一翻的超速法,最大限度地减少偏离目标的情况。实验结果表明,拟议采用超越控制式方案编制方法,快速找到一套可坐式解决方案的功效。
相关内容
微信扫码咨询专知VIP会员