IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)
Gaussian Process Bayesian Optimization for QUBO Penalty Weight Auto-Setting on a Distributed Quantum and Quantum-Inspired Annealing Platform
Jehn‐Ruey Jiang, Dai-Lun Chiang, Wen‐Han Huang
Abstract
This paper proposes the use of Gaussian process Bayesian optimization (GPBO) to address the challenging problem of penalty weight auto-setting (PWAS) in quadratic unconstrained binary optimization (QUBO) formulations on a distributed quantum and quantum-inspired annealing platform called National Central University Annealer (NCUA). The GPBO approach is compared with a PWAS method, namely maximum QUBO coefficient (MQC), to show its superiority.