Transpiler Autotuning with Predictive Models for Quantum Circuit Optimization

2026-07-31

AI Summary

This work proposes a supervised learning–based auto-tuning approach to overcome the limitations of fixed-configuration optimization in traditional quantum circuit transpilation, which often fails to achieve optimal two-qubit gate reduction across diverse circuits. By integrating circuit feature modeling with machine learning, the method dynamically selects the best combination of optimization passes for the Qiskit transpiler. Trained on the MQT Bench benchmark suite, the predictive model transcends the constraints of predefined optimization levels. Experimental results demonstrate that, compared to Qiskit’s default settings, the proposed approach reduces two-qubit gate counts by an additional 19.1%–32.4% on average, with some circuits achieving up to a 95.8% reduction, thereby substantially enhancing transpilation efficiency.

Abstract

Quantum software engineering is an emerging research field focusing on efficiently embedding the quantum programming paradigm into existing software ecosystems. A key aspect of this field is the realization of quantum algorithms using gate-based programming and the subsequent low-level optimization of the resulting quantum circuits, a process that is commonly performed by so-called transpilation pipelines. One significant challenge in these pipelines is determining which optimizations to apply to a given circuit. This decision is usually based on fixed default configurations that are uniformly applied to all circuits, frequently resulting in missed opportunities for more aggressive circuit optimization. In this work, we tackle this challenge by applying autotuning with supervised machine learning to develop an automated method for selection of transpiler passes. To train our machine-learning models, we employ feature-model based sampling to generate a representative dataset that examines how different combinations of Qiskit transpiler passes perform across thousands of circuits drawn from the state-of-the-art benchmarking suite MQT Bench. Using these data, we build a predictive model extension for the Qiskit transpilation pipeline that uses a machine learning model to automatically select combinations of transpiler passes aiming to achieve a maximum reduction in two-qubit gates. Our empirical evaluation shows that the combinations selected by our model are never outperformed by Qiskit's optimization levels, achieve on average an additional 19.1$\%$ - 32.4$\%$ reduction in two-qubit gates, and for some circuits finds reductions of up to $95.8\%$ in cases where Qiskit achieves no reduction at all.

Problem

• quantum circuit optimization
• transpiler autotuning
• two-qubit gate reduction
• quantum software engineering
• transpilation pipeline

Innovation

• quantum circuit optimization
• transpiler autotuning
• machine learning for quantum software
• Qiskit transpilation
• two-qubit gate reduction