The Unified Effect of Data Encoding, Ansatz Expressibility and Entanglement on the Trainability of HQNNs

Abstract

In this paper, we propose a framework to study the combined effect of several factors that contribute to the barren plateau problem in quantum neural networks (QNNs), which is a critical challenge in quantum machine learning (QML). These factors include data encoding, qubit entanglement, and ansatz expressibility. To investigate this joint effect in a real-world context, we focus on hybrid quantum neural networks (HQNNs) for multi-class classification. Our proposed framework aims to analyze the impact of these factors on the training landscape of HQNNs. Our findings show that the barren plateau problem in HQNNs is dependent on the expressibility of the underlying ansatz and the type of data encoding. Furthermore, we observe that entanglement also plays a role in the barren plateau problem. By evaluating the performance of HQNNs with various evaluation metrics for classification tasks, we provide recommendations for different constraint scenarios, highlighting the significance of our framework for the practical success of QNNs.

References in corpus (48)

• Quantum Computing in the NISQ era and beyond
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Quantum Machine Learning
• A variational eigenvalue solver on a quantum processor
• Variational Quantum Algorithms
• Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
• Supervised learning with quantum enhanced feature spaces
• Quantum computational advantage using photons
• Barren plateaus in quantum neural network training landscapes
• The theory of variational hybrid quantum-classical algorithms
• Quantum support vector machine for big data classification
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Quantum Convolutional Neural Networks
• Strong quantum computational advantage using a superconducting quantum processor
• Parameterized quantum circuits as machine learning models
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Evaluating analytic gradients on quantum hardware
• Circuit-centric quantum classifiers
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Towards Practical Quantum Variational Algorithms
• Efficient Learning for Deep Quantum Neural Networks
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Generalized Unitary Coupled Cluster Wavefunctions for Quantum Computation
• Quantum-Classical Computation of Schwinger Model Dynamics using Quantum Computers
• Continuous-variable quantum neural networks
• An initialization strategy for addressing barren plateaus in parametrized quantum circuits
• Layerwise learning for quantum neural networks
• Robust data encodings for quantum classifiers
• Hierarchical quantum classifiers
• Quantum generalisation of feedforward neural networks
• Effect of barren plateaus on gradient-free optimization
• PennyLane: Automatic differentiation of hybrid quantum-classical computations
• Variational Quantum State Diagonalization
• Noise Resilience of Variational Quantum Compiling
• Trainability of Dissipative Perceptron-Based Quantum Neural Networks
• Digitization of Scalar Fields for Quantum Computing
• Large gradients via correlation in random parameterized quantum circuits
• Universal Variational Quantum Computation
• Unitary quantum perceptron as efficient universal approximator
• Quantum implementation of an artificial feed-forward neural network
• Analysis and synthesis of feature map for kernel-based quantum classifier
• ResQNets: A Residual Approach for Mitigating Barren Plateaus in Quantum Neural Networks
• A Grover-search Based Quantum Learning Scheme for Classification
• Modeling and mitigation of cross-talk effects in readout noise with applications to the Quantum Approximate Optimization Algorithm
• Cost function embedding and dataset encoding for machine learning with parameterized quantum circuits
• Effects of Quantum Noise on Quantum Approximate Optimization Algorithm
• Quantum Mean Embedding of Probability Distributions

Cited by in corpus (7)

• Barren Plateaus in Variational Quantum Computing
• Does provable absence of barren plateaus imply classical simulability?
• ResQNets: A Residual Approach for Mitigating Barren Plateaus in Quantum Neural Networks
• Next-Generation Quantum Neural Networks: Enhancing Efficiency, Security, and Privacy
• Investigating the Effect of Noise on the Training Performance of Hybrid Quantum Neural Networks
• Physical Realization of Measurement Based Quantum Computation
• HQNET: Harnessing Quantum Noise for Effective Training of Quantum Neural Networks in NISQ Era