Saved in:
Bibliographic Details
Main Authors: Dubal, Ayushi, Kremer, David, Martiel, Simon, Villar, Victor, Wang, Derek, Cruz-Benito, Juan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.14448
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909541452480512
author Dubal, Ayushi
Kremer, David
Martiel, Simon
Villar, Victor
Wang, Derek
Cruz-Benito, Juan
author_facet Dubal, Ayushi
Kremer, David
Martiel, Simon
Villar, Victor
Wang, Derek
Cruz-Benito, Juan
contents We introduce a Reinforcement Learning (RL)-based method for re-synthesis of quantum circuits containing arbitrary Pauli rotations alongside Clifford operations. By collapsing each sub-block to a compact representation and then synthesizing it step-by-step through a learned heuristic, we obtain circuits that are both shorter and compliant with hardware connectivity constraints. We find that the method is fast enough and good enough to work as an optimization procedure: in direct comparisons on 6-qubit random Pauli Networks against state-of-the-art heuristic methods, our RL approach yields over 2x reduction in two-qubit gate count, while executing in under 10 milliseconds per circuit. We further integrate the method into a collect-and-re-synthesize pipeline, applied as a Qiskit transpiler pass, where we observe average improvements of 20% in two-qubit gate count and depth, reaching up to 60% for many instances, across the Benchpress benchmark. These results highlight the potential of RL-driven synthesis to significantly improve circuit quality in realistic, large-scale quantum transpilation workloads.
format Preprint
id arxiv_https___arxiv_org_abs_2503_14448
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pauli Network Circuit Synthesis with Reinforcement Learning
Dubal, Ayushi
Kremer, David
Martiel, Simon
Villar, Victor
Wang, Derek
Cruz-Benito, Juan
Quantum Physics
Artificial Intelligence
We introduce a Reinforcement Learning (RL)-based method for re-synthesis of quantum circuits containing arbitrary Pauli rotations alongside Clifford operations. By collapsing each sub-block to a compact representation and then synthesizing it step-by-step through a learned heuristic, we obtain circuits that are both shorter and compliant with hardware connectivity constraints. We find that the method is fast enough and good enough to work as an optimization procedure: in direct comparisons on 6-qubit random Pauli Networks against state-of-the-art heuristic methods, our RL approach yields over 2x reduction in two-qubit gate count, while executing in under 10 milliseconds per circuit. We further integrate the method into a collect-and-re-synthesize pipeline, applied as a Qiskit transpiler pass, where we observe average improvements of 20% in two-qubit gate count and depth, reaching up to 60% for many instances, across the Benchpress benchmark. These results highlight the potential of RL-driven synthesis to significantly improve circuit quality in realistic, large-scale quantum transpilation workloads.
title Pauli Network Circuit Synthesis with Reinforcement Learning
topic Quantum Physics
Artificial Intelligence
url https://arxiv.org/abs/2503.14448