Quantum Architecture Search for Solving Quantum Machine Learning Tasks

2025-09-14

AI Summary

Current quantum hardware suffers from high noise levels and limited scale, hindering the design of efficient, hardware-friendly quantum architecture search (QAS) methods for quantum machine learning (QML) classification tasks. Method: This paper proposes RL-QAS—the first framework to systematically apply reinforcement learning to automated quantum circuit architecture search. Built upon a quantum-classical hybrid paradigm, RL-QAS jointly optimizes both the topology and parameters of variational quantum circuits under strict constraints on circuit complexity, enabling end-to-end autonomous design. Contribution/Results: Experiments on the Iris and binary MNIST datasets demonstrate that architectures discovered by RL-QAS significantly improve test accuracy under realistic noise conditions. The resulting circuits exhibit strong hardware compatibility and generalization capability. This work establishes a novel paradigm for constructing scalable and robust QML models.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Multiagent Systems: Multiagent Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Security and privacy of machine learning and AI applications

Abstract

Quantum computing leverages quantum mechanics to address computational problems in ways that differ fundamentally from classical approaches. While current quantum hardware remains error-prone and limited in scale, Variational Quantum Circuits offer a noise-resilient framework suitable for today's devices. The performance of these circuits strongly depends on the underlying architecture of their parameterized quantum components. Identifying efficient, hardware-compatible quantum circuit architectures -- known as Quantum Architecture Search (QAS) -- is therefore essential. Manual QAS is complex and error-prone, motivating efforts to automate it. Among various automated strategies, Reinforcement Learning (RL) remains underexplored, particularly in Quantum Machine Learning contexts. This work introduces RL-QAS, a framework that applies RL to discover effective circuit architectures for classification tasks. We evaluate RL-QAS using the Iris and binary MNIST datasets. The agent autonomously discovers low-complexity circuit designs that achieve high test accuracy. Our results show that RL is a viable approach for automated architecture search in quantum machine learning. However, applying RL-QAS to more complex tasks will require further refinement of the search strategy and performance evaluation mechanisms.

Problem

• Automating quantum circuit architecture search using reinforcement learning
• Finding hardware-compatible quantum circuits for machine learning tasks
• Improving variational quantum circuit performance through optimized architecture design

Innovation

• Reinforcement Learning automates quantum circuit design
• RL-QAS framework discovers low-complexity quantum architectures
• Quantum Architecture Search applied to classification tasks