Training Optimization for Gate-Model Quantum Neural Networks

Abstract

Gate-based quantum computations represent an essential to realize near-term quantum computer architectures. A gate-model quantum neural network (QNN) is a QNN implemented on a gate-model quantum computer, realized via a set of unitaries with associated gate parameters. Here, we define a training optimization procedure for gate-model QNNs. By deriving the environmental attributes of the gate-model quantum network, we prove the constraint-based learning models. We show that the optimal learning procedures are different if side information is available in different directions, and if side information is accessible about the previous running sequences of the gate-model QNN. The results are particularly convenient for gate-model quantum computer implementations.

arXiv comment35 pages, Scientific Reports (2019)

References in corpus (39)

• Quantum Computing in the NISQ era and beyond
• Quantum Machine Learning
• Quantum support vector machine for big data classification
• A Quantum Approximate Optimization Algorithm
• Logic gates at the surface code threshold: Superconducting qubits poised for fault-tolerant quantum computing
• Quantum principal component analysis
• General Benchmarks for Quantum Repeaters
• Fundamental Limits of Repeaterless Quantum Communications
• An introduction to quantum machine learning
• Quantum Computational Supremacy
• Demonstration of a small programmable quantum computer with atomic qubits
• Recent Advances in Recurrent Neural Networks
• Quantum generative adversarial learning
• Quantum algorithms for supervised and unsupervised machine learning
• Quantum Internet: Networking Challenges in Distributed Quantum Computing
• Realization of a scalable Shor algorithm
• A Survey on Quantum Channel Capacities
• End-to-end capacities of a quantum communication network
• Quantum generalisation of feedforward neural networks
• Unitary Evolution Recurrent Neural Networks
• Quantum Supremacy through the Quantum Approximate Optimization Algorithm
• Theory of channel simulation and bounds for private communication
• A Quantum Approximate Optimization Algorithm Applied to a Bounded Occurrence Constraint Problem
• Quantum Neuron: an elementary building block for machine learning on quantum computers
• Unitary quantum perceptron as efficient universal approximator
• Quantum Algorithms for Fixed Qubit Architectures
• Decentralized Base-Graph Routing for the Quantum Internet
• General bounds for sender-receiver capacities in multipoint quantum communications
• Performance of the Quantum Approximate Optimization Algorithm on the Maximum Cut Problem
• Advances in Quantum Reinforcement Learning
• Entanglement-Gradient Routing for Quantum Networks
• Capacities of repeater-assisted quantum communications
• For Fixed Control Parameters the Quantum Approximate Optimization Algorithm's Objective Function Value Concentrates for Typical Instances
• Entanglement Availability Differentiation Service for the Quantum Internet
• A quantum speedup in machine learning: Finding a N-bit Boolean function for a classification
• Multilayer Optimization for the Quantum Internet
• Dense Quantum Measurement Theory
• Quantum algorithms for topological and geometric analysis of big data
• Artificial Quantum Neural Network: quantum neurons, logical elements and tests of convolutional nets

Cited by in corpus (10)

• Natural quantum reservoir computing for temporal information processing
• Optimizing High-Efficiency Quantum Memory with Quantum Machine Learning for Near-Term Quantum Devices
• Quantum State Optimization and Computational Pathway Evaluation for Gate-Model Quantum Computers
• Recurrent Quantum Neural Networks
• Speed-up Quantum Perceptron via Shortcuts to Adiabaticity
• Networked Quantum Services
• Quantum inspired qubit qutrit neural networks for real time financial forecasting
• Preparing Quantum States by Measurement-feedback Control with Bayesian Optimization
• The simulation of distributed quantum algorithms
• Quantum frequency resampling