Model-based optimization, in concert with conventional black-box methods, can quickly solve large-scale combinatorial problems. Recently, quantum-inspired modeling schemes based on tensor networks have been developed which have the potential to better identify and represent correlations in datasets. Here, we use a quantum-inspired model-based optimization method TN-GEO to assess the efficacy of these quantum-inspired methods when applied to realistic problems. In this case, the problem of interest is the optimization of a realistic assembly line based on BMW's currently utilized manufacturing schedule. Through a comparison of optimization techniques, we found that quantum-inspired model-based optimization, when combined with conventional black-box methods, can find lower-cost solutions in certain contexts.
@article{arxiv.2305.02179,
title = {Quantum Inspired Optimization for Industrial Scale Problems},
author = {William P. Banner and Shima Bab Hadiashar and Grzegorz Mazur and Tim Menke and Marcin Ziolkowski and Ken Kennedy and Jhonathan Romero and Yudong Cao and Jeffrey A. Grover and William D. Oliver},
journal= {arXiv preprint arXiv:2305.02179},
year = {2023}
}