Quantum Architecture Search with Meta-learning

Abstract

Variational quantum algorithms (VQAs) have been successfully applied to quantum approximate optimization algorithms, variational quantum compiling and quantum machine learning models. The performances of VQAs largely depend on the architecture of parameterized quantum circuits (PQCs). Quantum architecture search (QAS) aims to automate the design of PQCs in different VQAs with classical optimization algorithms. However, current QAS algorithms do not use prior experiences and search the quantum architecture from scratch for each new task, which is inefficient and time consuming. In this paper, we propose a meta quantum architecture search (MetaQAS) algorithm, which learns good initialization heuristics of the architecture (i.e., meta-architecture), along with the meta-parameters of quantum gates from a number of training tasks such that they can adapt to new tasks with a small number of gradient updates, which leads to fast learning on new tasks. The proposed MetaQAS can be used with arbitrary gradient-based QAS algorithms. Simulation results of variational quantum compiling on three- and four-qubit circuits show that the architectures optimized by MetaQAS converge much faster than a state-of-the-art gradient-based QAS algorithm, namely DQAS. MetaQAS also achieves a better solution than DQAS after fine-tuning of gate parameters.

References in corpus (45)

• Quantum Computing in the NISQ era and beyond
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Variational Quantum Algorithms
• Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
• Barren plateaus in quantum neural network training landscapes
• A Quantum Approximate Optimization Algorithm
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• An adaptive variational algorithm for exact molecular simulations on a quantum computer
• From the Quantum Approximate Optimization Algorithm to a Quantum Alternating Operator Ansatz
• Variational Quantum Computation of Excited States
• Transfer learning in hybrid classical-quantum neural networks
• An initialization strategy for addressing barren plateaus in parametrized quantum circuits
• Learning to reinforcement learn
• Quantum-assisted quantum compiling
• Differentiable Learning of Quantum Circuit Born Machine
• Variational quantum algorithms for discovering Hamiltonian spectra
• Unsupervised Machine Learning on a Hybrid Quantum Computer
• Structure optimization for parameterized quantum circuits
• Noise Resilience of Variational Quantum Compiling
• Quantum generative adversarial network for generating discrete distribution
• Differentiable Quantum Architecture Search
• Reachability Deficits in Quantum Approximate Optimization
• Low-depth gradient measurements can improve convergence in variational hybrid quantum-classical algorithms
• Machine learning of noise-resilient quantum circuits
• Quantum Optimization with a Novel Gibbs Objective Function and Ansatz Architecture Search
• Variational Quantum Reinforcement Learning via Evolutionary Optimization
• Topological Quantum Compiling with Reinforcement Learning
• Gradients of parameterized quantum gates using the parameter-shift rule and gate decomposition
• Neural Predictor based Quantum Architecture Search
• Universal discriminative quantum neural networks
• On the Universality of the Quantum Approximate Optimization Algorithm
• Learning to learn with quantum neural networks via classical neural networks
• Meta-Learning with Warped Gradient Descent
• Genetic Algorithms for Digital Quantum Simulations
• Reinforcement learning for optimization of variational quantum circuit architectures
• Markovian Quantum Neuroevolution for Machine Learning
• A Domain-agnostic, Noise-resistant, Hardware-efficient Evolutionary Variational Quantum Eigensolver
• MoG-VQE: Multiobjective genetic variational quantum eigensolver
• Variational quantum compiling with double Q-learning
• To quantum or not to quantum: towards algorithm selection in near-term quantum optimization
• Quantum Architecture Search via Deep Reinforcement Learning
• Variational circuit compiler for quantum error correction
• Automated Relational Meta-learning
• Variational Quantum Gate Optimization
• Compiling universal quantum circuits

Cited by in corpus (10)

• The Variational Quantum Eigensolver: a review of methods and best practices
• Quantum Architecture Search: A Survey
• Automated Quantum Circuit Design with Nested Monte Carlo Tree Search
• Distributed quantum architecture search
• GSQAS: Graph Self-supervised Quantum Architecture Search
• Machine Learning for Estimation and Control of Quantum Systems
• Quantum continual learning of quantum data realizing knowledge backward transfer
• Quantum Circuit Design using a Progressive Widening Enhanced Monte Carlo Tree Search
• Enhancing Variational Quantum Circuit Training: An Improved Neural Network Approach for Barren Plateau Mitigation
• Multi-target quantum compilation algorithm