analiza aiqbench
This research demonstrates that integrating real-time calibration data into graph reinforcement learning can significantly boost quantum circuit fidelity on superconducting processors, outperforming standard gate-count metrics like those used by SABRE. While the approach increases two-qubit operation counts for smaller circuits (5 and 8 qubits), it offers a crucial pathway to mitigate errors caused by poorly calibrated couplers in noisy intermediate-scale devices. The findings highlight a necessary shift from purely overhead-driven compilation strategies toward fidelity-aware routing that accounts for dynamic hardware states.
Graph Reinforcement Learning for Calibration-Aware Quantum Circuit Routing
arXiv:2606.12816v4 Announce Type: replace Abstract: Quantum circuit routing is a key step in compiling programs for noisy intermediate-scale quantum processors, particularly superconducting devices whose sparse fixed coupling makes routing a central compilation cost. Routes that appear efficient by standard overhead metrics such as SWAP count, routed two-qubit count, and depth can still lose fidelity when they pass through poorly calibrated couplers. We study a calibration-aware graph reinforcement-learning router that uses same-day calibration data from superconducting IBM Heron r2 processors to choose hardware-edge SWAPs. We train the policy with proximal policy optimization and evaluate it with exact simulated fidelity across nine Munich Quantum Toolkit (MQT) Bench circuits and three calibration snapshots. Across these evaluations, pooled mean exact fidelity is 0.727, compared with 0.440 for SWAP-based bidirectional heuristic search (SABRE)-best20 and 0.481 for target-aware SABRE. We observe that fidelity gains come with higher routed two-qubit counts and are concentrated in 5 qubit and 8 qubit circuit families; under the fixed tree action graph, all 10 qubit families favor SABRE-best20. Overall, our results show that calibration-aware learned routing can improve fidelity beyond gate-count-driven compilation, by roughly 0.25 to 0.29 in absolute mean fidelity over the SABRE-family baselines.
Abstract:Quantum circuit routing is a key step in compiling programs for noisy intermediate-scale quantum processors, particularly superconducting devices whose sparse fixed coupling makes routing a central compilation cost. Routes that appear efficient by standard overhead metrics such as SWAP count, routed two-qubit count, and depth can still lose fidelity when they pass through poorly calibrated couplers. We study a calibration-aware graph reinforcement-learning router that uses same-day calibration data from superconducting IBM Heron r2 processors to choose hardware-edge SWAPs. We train the policy with proximal policy optimization and evaluate it with exact simulated fidelity across nine Munich Quantum Toolkit (MQT) Bench circuits and three calibration snapshots. Across these evaluations, pooled mean exact fidelity is 0.727, compared with 0.440 for SWAP-based bidirectional heuristic search (SABRE)-best20 and 0.481 for target-aware SABRE. We observe that fidelity gains come with higher routed two-qubit counts and are concentrated in 5 qubit and 8 qubit circuit families; under the fixed tree action graph, all 10 qubit families favor SABRE-best20. Overall, our results show that calibration-aware learned routing can improve fidelity beyond gate-count-driven compilation, by roughly 0.25 to 0.29 in absolute mean fidelity over the SABRE-family baselines.
Quantum Physics (quant-ph); Emerging Technologies (cs.ET); Machine Learning (cs.LG)
arXiv:2606.12816 [quant-ph]
(or arXiv:2606.12816v4 [quant-ph] for this version)
Text integral sub licența deschisă a publicației · 206 cuvinte
Subiecte conexe
Graph Reinforcement Learning for Calibration-Aware Quantum Circuit Routing
arXiv · 12 iun. 2026
Graph neural network predicts qubit routing costs
Quantum Zeitgeist · 18 sept. 2026
AI and Quantum Computing Briefing
livetradingnews.com · 4 aug. 2026
News
Quantum Computing Report · 25 iul. 2026