Introduction to Quantum Machine Learning and Quantum Architecture Search
Samuel Yen-Chi Chen, Zhiding Liang
TL;DR
The paper surveys the intersection of quantum computing and machine learning, focusing on variational quantum circuits and their hybrid quantum–classical training. It covers QML architectures across classification, sequential learning, NLP, RL, and model compression, and surveys quantum architecture search (QAS) approaches including RL, evolutionary, and differentiable methods, with attention to DiffQAS that optimizes circuit structure alongside QNN parameters via gradient methods. A key contribution is the discussion of Quantum‑Train (QT) for generating classical NN weights from quantum measurements, and the framing of QAS as an automated driver of high‑performance quantum models under hardware constraints, exemplified by ensemble and differentiable strategies. The work emphasizes the practical potential of integrating quantum resources with automated design to broaden QML applicability and efficiency on near‑term devices.
Abstract
Recent advancements in quantum computing (QC) and machine learning (ML) have fueled significant research efforts aimed at integrating these two transformative technologies. Quantum machine learning (QML), an emerging interdisciplinary field, leverages quantum principles to enhance the performance of ML algorithms. Concurrently, the exploration of systematic and automated approaches for designing high-performance quantum circuit architectures for QML tasks has gained prominence, as these methods empower researchers outside the quantum computing domain to effectively utilize quantum-enhanced tools. This tutorial will provide an in-depth overview of recent breakthroughs in both areas, highlighting their potential to expand the application landscape of QML across diverse fields.