FIDDLE: Reinforcement Learning for Quantum Fidelity Enhancement

2025-10-17

AI Summary

Quantum circuit routing on noisy intermediate-scale quantum (NISQ) devices suffers from low process fidelity due to hardware constraints and noise. Traditional routing methods optimize indirect proxies—such as circuit depth or gate count—rather than fidelity itself, leading to suboptimal performance. Method: This paper proposes an end-to-end optimization framework that jointly leverages reinforcement learning (RL) and a Gaussian process (GP) surrogate model. Crucially, it directly optimizes for process fidelity—a first in quantum routing—enabling accurate fidelity modeling during routing. The GP surrogate efficiently estimates fidelity from minimal circuit evaluations, drastically reducing computational overhead; RL then uses these estimates to learn high-fidelity routing policies. Results: Experiments across diverse noise models demonstrate significant fidelity improvements over state-of-the-art routing algorithms. The GP surrogate achieves higher fidelity estimation accuracy than existing approaches, and the integrated framework consistently outperforms mainstream routing techniques in both fidelity and scalability.

Technology Category

• Planning, Routing, and Scheduling: Routing
• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

Quantum computing has the potential to revolutionize fields like quantum optimization and quantum machine learning. However, current quantum devices are hindered by noise, reducing their reliability. A key challenge in gate-based quantum computing is improving the reliability of quantum circuits, measured by process fidelity, during the transpilation process, particularly in the routing stage. In this paper, we address the Fidelity Maximization in Routing Stage (FMRS) problem by introducing FIDDLE, a novel learning framework comprising two modules: a Gaussian Process-based surrogate model to estimate process fidelity with limited training samples and a reinforcement learning module to optimize routing. Our approach is the first to directly maximize process fidelity, outperforming traditional methods that rely on indirect metrics such as circuit depth or gate count. We rigorously evaluate FIDDLE by comparing it with state-of-the-art fidelity estimation techniques and routing optimization methods. The results demonstrate that our proposed surrogate model is able to provide a better estimation on the process fidelity compared to existing learning techniques, and our end-to-end framework significantly improves the process fidelity of quantum circuits across various noise models.

Problem

• Enhancing quantum circuit reliability through fidelity optimization
• Addressing noise limitations in gate-based quantum computing
• Optimizing quantum routing using reinforcement learning techniques

Innovation

• Gaussian Process surrogate model estimates quantum fidelity
• Reinforcement learning optimizes quantum circuit routing
• Directly maximizes process fidelity outperforming indirect metrics