Combinatorial optimization problems are crucial in many scientific and engineering applications, yet their solutions remain challenging due to exponentially large search spaces. Variational quantum algorithms offer a promising route for tackling such problems, yet their practical performance is limited by repeated quantum circuit evaluations and classical parameter updates. This work introduces DQAOA-GPT, a hybrid framework that integrates the distributed quantum approximate optimization algorithm (DQAOA), which decomposes a large optimization problem into smaller sub-problems, with GPT-based quantum circuit generation for solving those sub-problems.
Rather than relying on iterative variational optimization, the proposed approach uses a trained generative model to directly generate high-quality quantum circuits for the decomposed sub-problems. As a benchmark, we evaluate DQAOA-GPT against conventional DQAOA on dense HUBO optimization problems with up to 100 decision variables. The results demonstrate that DQAOA-GPT significantly reduces computational cost while maintaining competitive solution quality, with larger acceleration observed for larger sub-problem sizes. Although this work focuses on benchmark-scale validation, the framework provides a promising foundation for larger-scale combinatorial optimization in hybrid HPC-QC environments through increased GPU resources and parallel computing capability.
Blogger's Review: DQAOA-GPT blends the strengths of quantum computing and AI, paving new paths for solving complex combinatorial optimization problems. By optimizing the circuit generation process, it not only enhances computational efficiency but also lays a foundation for future large-scale applications. This framework shows great potential in the integration of high-performance computing and quantum computing, making it a noteworthy development.