🤖 AI Summary
To address the high computational cost and the trade-off between solution quality and efficiency in training Quadratic Unconstrained Binary Optimization (QUBO) models for adiabatic quantum machine learning (AQML), this paper proposes a hybrid heuristic algorithm integrating an *r*-flip local search. We introduce, for the first time, an *r*-flip neighborhood structure that significantly improves the balance between search efficiency and solution quality. The algorithm synergistically combines quantum-inspired heuristics, multi-start tabu search, and simulated annealing to yield a robust and scalable optimization framework. Experimental evaluation on standard benchmarks and three large-scale QUBO instances demonstrates that our method achieves, on average, a 12.7% improvement in solution quality and a 38.5% reduction in runtime compared to conventional multi-start tabu search (MSTS). These results meet the stringent requirements of AQML for both accuracy and real-time deployability.
📝 Abstract
Numerous established machine learning models and various neural network architectures can be restructured as Quadratic Unconstrained Binary Optimization (QUBO) problems. A significant challenge in Adiabatic Quantum Machine Learning (AQML) is the computational demand of the training phase. To mitigate this, approximation techniques inspired by quantum annealing, like Simulated Annealing and Multiple Start Tabu Search (MSTS), have been employed to expedite QUBO-based AQML training. This paper introduces a novel hybrid algorithm that incorporates an"r-flip"strategy. This strategy is aimed at solving large-scale QUBO problems more effectively, offering better solution quality and lower computational costs compared to existing MSTS methods. The r-flip approach has practical applications in diverse fields, including cross-docking, supply chain management, machine scheduling, and fraud detection. The paper details extensive computational experiments comparing this r-flip enhanced hybrid heuristic against a standard MSTS approach. These tests utilize both standard benchmark problems and three particularly large QUBO instances. The results indicate that the r-flip enhanced method consistently produces high-quality solutions efficiently, operating within practical time constraints.