DQAOA-GPT: AI-Accelerated Distributed Quantum Optimization for Combinatorial Problems

2026-07-22

AI Summary

This work addresses the computational challenges of combinatorial optimization problems, whose exponentially growing search spaces are further exacerbated in variational quantum algorithms by repeated cost evaluations and parameter updates. To overcome this bottleneck, the authors propose DQAOA-GPT, a hybrid framework that integrates generative AI into quantum optimization for the first time. Specifically, a pretrained GPT model directly generates high-quality quantum circuits for decomposed subproblems, bypassing conventional iterative optimization. The approach synergistically combines distributed Quantum Approximate Optimization Algorithm (DQAOA), automated quantum circuit synthesis, and GPU-accelerated parallel computation. Evaluated on dense higher-order unconstrained binary optimization (HUBO) instances with up to 100 variables, the method substantially reduces computational overhead while maintaining competitive solution quality, with greater acceleration observed as subproblem size increases.

Abstract

While combinatorial optimization problems are central to many scientific and engineering applications, their solution remains 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. In this work, we introduce 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.

Problem

• combinatorial optimization
• quantum algorithms
• search space
• variational optimization
• HUBO

Innovation

• DQAOA-GPT
• generative quantum circuit synthesis
• distributed quantum optimization
• combinatorial optimization
• variational quantum algorithms