Q-RLONAS: Towards Efficient Quantum Neural Architecture Search
- 30 August 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 01, 1756-1765
Abstract
Quantum neural architecture search aims to automate the design of parameterized quantum circuits (PQCs) within quantum neural networks (QNNs), where learning performance is highly sensitive to the placement and type of quantum gates. However, applying traditional NAS techniques to quantum circuits presents significant challenges, including barren plateaus, noise accumulation, device-specific constraints, and the high computational cost of independently evaluating all candidate architectures. To address these limitations, this paper proposes Q-RLONAS, a two-stage quantum NAS framework that integrates deep reinforcement learning (DRL) with one-shot NAS to efficiently explore and optimize PQC structures. In the Stage #1, DRL determines the optimal gate placement by leveraging a reward function that considers performance, noise, barren plateaus, and hardware constraints. In the Stage #2, a one-shot NAS method is employed to select effective quantum gate types using weight sharing within a supernet, significantly reducing training overhead. Experimental results on the mini-MNIST dataset demonstrate that Q-RLONAS achieves high accuracy while satisfying gate placement constraints, outperforming existing approaches in terms of efficiency for quantum circuit design.Keywords
Funding Information
- Ministry of Science and ICT (IITP-2025-RS-2024-00436887)
This publication has 22 references indexed in Scilit:
- Transition role of entangled data in quantum machine learningNature Communications, 2024
- High-fidelity parallel entangling gates on a neutral-atom quantum computerNature, 2023
- Neurotrie: Deep Reinforcement Learning-based Fast Software IPv6 Lookup2022
- Quantum Multi-Agent Reinforcement Learning via Variational Quantum Circuit Design2022
- Quantum circuit architecture search for variational quantum algorithmsnpj Quantum Information, 2022
- QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits2022
- Deep Reinforcement Learning Based VNF Management in Geo-distributed Edge Computing2019
- Barren plateaus in quantum neural network training landscapesNature Communications, 2018
- Quantum circuit learningPhysical Review A, 2018
- Learning Transferable Architectures for Scalable Image Recognition2018