Toward Trainability of Quantum Neural Networks

Abstract

Quantum Neural Networks (QNNs) have been recently proposed as generalizations of classical neural networks to achieve the quantum speed-up. Despite the potential to outperform classical models, serious bottlenecks exist for training QNNs; namely, QNNs with random structures have poor trainability due to the vanishing gradient with rate exponential to the input qubit number. The vanishing gradient could seriously influence the applications of large-size QNNs. In this work, we provide a viable solution with theoretical guarantees. Specifically, we prove that QNNs with tree tensor and step controlled architectures have gradients that vanish at most polynomially with the qubit number. We numerically demonstrate QNNs with tree tensor and step controlled structures for the application of binary classification. Simulations show faster convergent rates and better accuracy compared to QNNs with random structures.

11 pages, 5 figures, 1 table

References in corpus (16)

• Quantum Machine Learning
• Quantum algorithm for solving linear systems of equations
• Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
• Recurrent Neural Network Regularization
• Barren plateaus in quantum neural network training landscapes
• Quantum support vector machine for big data classification
• Circuit-centric quantum classifiers
• Efficient Learning for Deep Quantum Neural Networks
• Quantum advantage with shallow circuits
• Layerwise learning for quantum neural networks
• Random Quantum Circuits are Approximate 2-designs
• PennyLane: Automatic differentiation of hybrid quantum-classical computations
• Trainability of Dissipative Perceptron-Based Quantum Neural Networks
• Circuit-Based Quantum Random Access Memory for Classical Data
• Gradients of parameterized quantum gates using the parameter-shift rule and gate decomposition
• Quantum Algorithms for Deep Convolutional Neural Networks

Cited by in corpus (21)

• The Variational Quantum Eigensolver: a review of methods and best practices
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Absence of Barren Plateaus in Quantum Convolutional Neural Networks
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Solving nonlinear differential equations with differentiable quantum circuits
• Equivalence of quantum barren plateaus to cost concentration and narrow gorges
• Efficient measure for the expressivity of variational quantum algorithms
• Quantum Machine Learning: from physics to software engineering
• Variational Quantum Classifiers Through the Lens of the Hessian
• Reduction of finite sampling noise in quantum neural networks
• Beyond unital noise in variational quantum algorithms: noise-induced barren plateaus and limit sets
• On exploring the potential of quantum auto-encoder for learning quantum systems
• VQE Method: A Short Survey and Recent Developments
• Expressivity of Variational Quantum Machine Learning on the Boolean Cube
• Qsun: an open-source platform towards practical quantum machine learning applications
• Speedy Contraction of ZX Diagrams with Triangles via Stabiliser Decompositions
• Quantum Graph Convolutional Neural Networks
• qLEET: Visualizing Loss Landscapes, Expressibility, Entangling Power and Training Trajectories for Parameterized Quantum Circuits
• Mitigating Noise-Induced Gradient Vanishing in Variational Quantum Algorithm Training
• Quantum Algorithms for Unsupervised Machine Learning and Neural Networks
• A Quantum Convolutional Neural Network for Image Classification