Hierarchical quantum circuit representations for neural architecture search

Abstract

Machine learning with hierarchical quantum circuits, usually referred to as Quantum Convolutional Neural Networks (QCNNs), is a promising prospect for near-term quantum computing. The QCNN is a circuit model inspired by the architecture of Convolutional Neural Networks (CNNs). CNNs are successful because they do not need manual feature design and can learn high-level features from raw data. Neural Architecture Search (NAS) builds on this success by learning network architecture and achieves state-of-the-art performance. However, applying NAS to QCNNs presents unique challenges due to the lack of a well-defined search space. In this work, we propose a novel framework for representing QCNN architectures using techniques from NAS, which enables search space design and architecture search. Using this framework, we generate a family of popular QCNNs, those resembling reverse binary trees. We then evaluate this family of models on a music genre classification dataset, GTZAN, to justify the importance of circuit architecture. Furthermore, we employ a genetic algorithm to perform Quantum Phase Recognition (QPR) as an example of architecture search with our representation. This work provides a way to improve model performance without increasing complexity and to jump around the cost landscape to avoid barren plateaus. Finally, we implement the framework as an open-source Python package to enable dynamic QCNN creation and facilitate QCNN search space design for NAS.

arXiv comment22 pages, 13 figures

References in corpus (38)

• Quantum Computing in the NISQ era and beyond
• Variational Quantum Algorithms
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Noisy intermediate-scale quantum (NISQ) algorithms
• Quantum Convolutional Neural Networks
• Machine learning phases of matter
• Parameterized quantum circuits as machine learning models
• An adaptive variational algorithm for exact molecular simulations on a quantum computer
• The power of quantum neural networks
• Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms
• Learning phase transitions by confusion
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• qubit-ADAPT-VQE: An adaptive algorithm for constructing hardware-efficient ansatze on a quantum processor
• Why does deep and cheap learning work so well?
• Quantum convolutional neural network for classical data classification
• Absence of Barren Plateaus in Quantum Convolutional Neural Networks
• Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
• Hierarchical quantum classifiers
• Quantum Computation of Electronic Transitions using a Variational Quantum Eigensolver
• Machine Learning Topological States
• Quantum Entanglement in Deep Learning Architectures
• Structure optimization for parameterized quantum circuits
• Exploiting symmetry in variational quantum machine learning
• Differentiable Quantum Architecture Search
• Group-Invariant Quantum Machine Learning
• Generalization in Quantum Machine Learning: a Quantum Information Perspective
• Statistical mechanics of the Cluster-Ising model
• Qubit-excitation-based adaptive variational quantum eigensolver
• Capacity and quantum geometry of parametrized quantum circuits
• Realizing Quantum Convolutional Neural Networks on a Superconducting Quantum Processor to Recognize Quantum Phases
• Quantum computing models for artificial neural networks
• Identifying optimal cycles in quantum thermal machines with reinforcement-learning
• Quantum Optimization with a Novel Gibbs Objective Function and Ansatz Architecture Search
• Neural Predictor based Quantum Architecture Search
• Markovian Quantum Neuroevolution for Machine Learning

Cited by in corpus (6)

• Optimizing Quantum Convolutional Neural Network Architectures for Arbitrary Data Dimension
• Pulsar Classification: Comparing Quantum Convolutional Neural Networks and Quantum Support Vector Machines
• Quantum Circuit Design using a Progressive Widening Enhanced Monte Carlo Tree Search
• Generating Generalised Ground-State Ansatzes from Few-Body Examples
• Optimizing Compilation for Distributed Quantum Computing via Clustering and Annealing
• Schmidt quantum compressor