From Characterization To Construction: Generative Quantum Circuit Synthesis from Gate Set Tomography Data

2026-05-02

AI Summary

This work addresses the limitations of traditional quantum compilation, which neglects complex correlated noise—such as crosstalk and drift—in quantum hardware, thereby constraining circuit fidelity. The authors propose a Quantum Machine Learning Control (QMLC) framework that, for the first time, enables end-to-end generation of hardware-native quantum circuits directly from raw gate set tomography (GST) data, bypassing the conventional two-stage “characterization–decomposition” pipeline. By employing curriculum learning to embed labeled GST germ circuits, the method constructs a context-aware generative latent space using a Set Vision Transformer with permutation-invariant pooling, and integrates an unconditional diffusion model enhanced by a denoising mechanism based on target covariance matrices. Experiments demonstrate that QMLC can generate high-fidelity, robust quantum circuits tailored to user-specified target measurement distributions, offering a novel compilation paradigm for near-term quantum devices with complex calibration requirements.

Abstract

High-fidelity circuit execution on noisy intermediate-scale quantum devices is bottlenecked by compilation pipelines that disregard complex, correlated noise. To address this, this methodology article proposes a quantum machine learning control (QMLC) framework for generative quantum circuit synthesis from gate-set tomography (GST) data that bypasses the traditional two-step pipeline of characterizing native quantum gates via GST followed by unitary decomposition algorithms. Instead, a generative concept space is directly learnt from GST data, enabling conditional synthesis of quantum circuits on a desired output distribution. Our approach tokenizes GST germ circuits and embeds them into a structured latent space using a curriculum-learning-motivated strategy, starting with short circuits and progressively incorporating longer ones with diverse output statistics. The embedded sequences are processed by a set-vision transformer with permutation-invariant pooling, producing k-seed vectors that represent the learned concept space of the quantum device. Aggregating data across multiple circuits makes this latent representation inherently context-aware, capturing the shared physical noise environment (e.g., crosstalk, drift) that isolated gate metrics miss. We propose an unconditional diffusion model to sample from the concept space. During inference, a user provides a target measurement distribution, and the model generates a corresponding circuit. To ensure fidelity and robustness, the output is denoised using a diffusion model that operates on the target conditional covariance matrix. This end-to-end framework is a step towards context-aware, hardware-native circuit synthesis directly from raw GST data, which offers a new paradigm for integrating quantum control and compilation. The QMLC framework is particularly suited for near-term quantum devices with complex calibration procedures.

Problem

• quantum circuit synthesis
• noisy intermediate-scale quantum devices
• correlated noise
• gate-set tomography
• hardware-native compilation

Innovation

• Generative Quantum Circuit Synthesis
• Gate Set Tomography
• Quantum Machine Learning Control
• Context-Aware Compilation
• Diffusion Model