Leveraging Diffusion Models for Parameterized Quantum Circuit Generation

2025-05-27

AI Summary

Quantum circuit design remains a critical bottleneck hindering the practical deployment of quantum computing, particularly in the joint optimization of parametrized quantum circuit (PQC) architecture and continuous parameters. To address this, we propose the first end-to-end generative framework for PQCs based on conditional denoising diffusion models, unifying the modeling of both discrete circuit topologies and continuous gate parameters. Our approach enables generalization across diverse native gate sets and qubit scales. Innovatively, we integrate diffusion modeling into PQC co-generation, guided by quantum state fidelity as the optimization objective and leveraging a continuous parameterized gate embedding strategy. Empirical evaluation demonstrates >99.5% fidelity in GHZ state preparation and 98.2% classification accuracy on quantum machine learning benchmarks—substantially outperforming existing variational search baselines.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Computer Vision: Diffusion Models for Vision

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Quantum computing holds immense potential, yet its practical success depends on multiple factors, including advances in quantum circuit design. In this paper, we introduce a generative approach based on denoising diffusion models (DMs) to synthesize parameterized quantum circuits (PQCs). Extending the recent diffusion model pipeline of F""urrutter et al. [1], our model effectively conditions the synthesis process, enabling the simultaneous generation of circuit architectures and their continuous gate parameters. We demonstrate our approach in synthesizing PQCs optimized for generating high-fidelity Greenberger-Horne-Zeilinger (GHZ) states and achieving high accuracy in quantum machine learning (QML) classification tasks. Our results indicate a strong generalization across varying gate sets and scaling qubit counts, highlighting the versatility and computational efficiency of diffusion-based methods. This work illustrates the potential of generative models as a powerful tool for accelerating and optimizing the design of PQCs, supporting the development of more practical and scalable quantum applications.

Problem

• Generating parameterized quantum circuits using diffusion models
• Optimizing circuits for high-fidelity GHZ state generation
• Enhancing quantum machine learning classification accuracy

Innovation

• Diffusion models generate quantum circuits
• Simultaneous circuit and parameter synthesis
• Generalizes across gate sets and qubits