Unified reinforcement learning improves quantum compilation and scheduling
MQSS-Selector: RL-Guided Pass Selection for an MLIR Compilation Pipeline
Distributed, Parallel, and Cluster ComputingMachine LearningProgramming Languages
Summary
Today's quantum computers are still imperfect and need special optimizations to run programs well. The authors present a new tool that uses reinforcement learning, a kind of AI, to help pick the best optimization steps and schedule jobs all together. This improves how quantum programs are compiled and run on noisy devices. The method adapts dynamically to different program and device conditions while balancing goals like accuracy and speed.
What this means in practice
- •For quantum software engineers: Optimize quantum compilation passes and job scheduling in unified workflows to improve execution fidelity and overall performance on NISQ-era quantum systems.
- •For high performance computing teams: Integrate quantum and classical workflow optimizations through learning-based selection to enhance hybrid HPC-quantum infrastructure efficiency.
Authors
Andre Youssefi, Ercüment Kaya, Minh Chung, Jorge Echavarria, Laura B. Schulz, Martin Schulz
Abstract
High Performance Computing (HPC) and Quantum Computing (QC) systems are increasingly converging towards unified High Performance Computing-Quantum Computing (HPCQC) infrastructures, driven by a growing need to bridge classical and quantum workflows, which affects all levels of the system stack, from the hardware to compilers and runtimes, all the way to applications. However, today's QC devices are still in the Noisy Intermediate-Scale Quantum (NISQ) era, are error-prone and resource-limited, and therefore require specialized optimizations and topology mappings to achieve sufficient fidelity. This places special emphasis on proper compilation and optimization within the overall quantum software stack. Many existing stacks remain fragmented, with separate components responsible for device selection, compiler-pass optimization, and job queue scheduling. This paper proposes a unified, learning-based selector that integrates these disparate stages into a cohesive framework. Our proposed selector scheme leverages reinforcement learning and deep learning models that can be extended to simultaneously optimize multiple objectives -- such as fidelity, compilation time, and scheduling latency -- while dynamically adapting to circuit characteristics and device conditions.