Neural Predictor based Quantum Architecture Search

Abstract

Variational quantum algorithms (VQAs) are widely speculated to deliver quantum advantages for practical problems under the quantum-classical hybrid computational paradigm in the near term. Both theoretical and practical developments of VQAs share many similarities with those of deep learning. For instance, a key component of VQAs is the design of task-dependent parameterized quantum circuits (PQCs) as in the case of designing a good neural architecture in deep learning. Partly inspired by the recent success of AutoML and neural architecture search (NAS), quantum architecture search (QAS) is a collection of methods devised to engineer an optimal task-specific PQC. It has been proven that QAS-designed VQAs can outperform expert-crafted VQAs under various scenarios. In this work, we propose to use a neural network based predictor as the evaluation policy for QAS. We demonstrate a neural predictor guided QAS can discover powerful PQCs, yielding state-of-the-art results for various examples from quantum simulation and quantum machine learning. Notably, neural predictor guided QAS provides a better solution than that by the random-search baseline while using an order of magnitude less of circuit evaluations. Moreover, the predictor for QAS as well as the optimal ansatz found by QAS can both be transferred and generalized to address similar problems.

arXiv comment10.2 pages + supplemental materials, 10 figures

References in corpus (84)

• Auto-Encoding Variational Bayes
• Quantum Computing in the NISQ era and beyond
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Quantum Machine Learning
• A variational eigenvalue solver on a quantum processor
• Neural Architecture Search with Reinforcement Learning
• Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• The theory of variational hybrid quantum-classical algorithms
• A Quantum Approximate Optimization Algorithm
• Neural Architecture Search: A Survey
• Quantum machine learning in feature Hilbert spaces
• Quantum computational chemistry
• Quantum Circuit Learning
• Quantum Chemistry in the Age of Quantum Computing
• Quantum Convolutional Neural Networks
• Error mitigation for short-depth quantum circuits
• DARTS: Differentiable Architecture Search
• Predicting Many Properties of a Quantum System from Very Few Measurements
• Parameterized quantum circuits as machine learning models
• An adaptive variational algorithm for exact molecular simulations on a quantum computer
• Circuit-centric quantum classifiers
• Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms
• Noise-Induced Barren Plateaus in Variational Quantum Algorithms
• From the Quantum Approximate Optimization Algorithm to a Quantum Alternating Operator Ansatz
• Towards Practical Quantum Variational Algorithms
• Quantum generative adversarial learning
• Variational ansatz-based quantum simulation of imaginary time evolution
• Large-Scale Evolution of Image Classifiers
• Neural Architecture Optimization
• Quantum Approximate Optimization of Non-Planar Graph Problems on a Planar Superconducting Processor
• Variational Quantum Computation of Excited States
• Theory of variational quantum simulation
• Designing Neural Network Architectures using Reinforcement Learning
• An initialization strategy for addressing barren plateaus in parametrized quantum circuits
• A generative modeling approach for benchmarking and training shallow quantum circuits
• Quantum-assisted quantum compiling
• Variational quantum algorithms for nonlinear problems
• Efficient Architecture Search by Network Transformation
• Subspace-search variational quantum eigensolver for excited states
• Differentiable Learning of Quantum Circuit Born Machine
• Learning the quantum algorithm for state overlap
• Variational quantum simulation of general processes
• Random Search and Reproducibility for Neural Architecture Search
• Variational Fast Forwarding for Quantum Simulation Beyond the Coherence Time
• Reinforcement Learning with Neural Networks for Quantum Feedback
• From transistor to trapped-ion computers for quantum chemistry
• A Survey on Neural Architecture Search
• Variational Quantum Linear Solver
• Solving nonlinear differential equations with differentiable quantum circuits
• Noise Resilience of Variational Quantum Compiling
• Differentiable Quantum Architecture Search
• Reachability Deficits in Quantum Approximate Optimization
• Variational Quantum Eigensolver with Fewer Qubits
• An efficient quantum algorithm for the time evolution of parameterized circuits
• Quantum Optimization with a Novel Gibbs Objective Function and Ansatz Architecture Search
• The Quantum Approximate Optimization Algorithm Needs to See the Whole Graph: A Typical Case
• D-VAE: A Variational Autoencoder for Directed Acyclic Graphs
• Peephole: Predicting Network Performance Before Training
• Quantum Assisted Simulator
• Probabilistic Neural Architecture Search
• Genetic Algorithms for Digital Quantum Simulations
• Quantum Hamiltonian-Based Models and the Variational Quantum Thermalizer Algorithm
• Analyzing the Performance of Variational Quantum Factoring on a Superconducting Quantum Processor
• AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search
• A Variational Quantum Algorithm for Preparing Quantum Gibbs States
• Markovian Quantum Neuroevolution for Machine Learning
• Approximate Quantum Adders with Genetic Algorithms: An IBM Quantum Experience
• Low depth mechanisms for quantum optimization
• MoG-VQE: Multiobjective genetic variational quantum eigensolver
• A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS
• Limitations of optimization algorithms on noisy quantum devices
• Variational quantum Gibbs state preparation with a truncated Taylor series
• A hybrid scheme for prime factorization and its experimental implementation using IBM quantum processor
• NASGEM: Neural Architecture Search via Graph Embedding Method
• A Variational-Sequential Graph Autoencoder for Neural Architecture Performance Prediction
• Variational Quantum Gate Optimization
• Neural Architecture Optimization with Graph VAE
• Balanced One-shot Neural Architecture Optimization
• Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks
• VSQL: Variational Shadow Quantum Learning for Classification
• Efficient Sampling for Predictor-Based Neural Architecture Search
• Disentangled Neural Architecture Search

Cited by in corpus (14)

• The Variational Quantum Eigensolver: a review of methods and best practices
• QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits
• Artificial Intelligence and Machine Learning for Quantum Technologies
• TensorCircuit: a Quantum Software Framework for the NISQ Era
• Near-Term Quantum Computing Techniques: Variational Quantum Algorithms, Error Mitigation, Circuit Compilation, Benchmarking and Classical Simulation
• Variational Quantum-Neural Hybrid Eigensolver
• Quantum Architecture Search with Meta-learning
• Quantum Architecture Search via Deep Reinforcement Learning
• Probing many-body localization by excited-state VQE
• Hierarchical quantum circuit representations for neural architecture search
• Automated Quantum Circuit Design with Nested Monte Carlo Tree Search
• GSQAS: Graph Self-supervised Quantum Architecture Search
• Supervised learning of random quantum circuits via scalable neural networks
• Accelerating variational quantum algorithms with multiple quantum processors