Quantum-data-driven dynamical transition in quantum learning

Abstract

Quantum neural networks, parameterized quantum circuits optimized under a specific cost function, provide a paradigm for achieving near-term quantum advantage in quantum information processing. Understanding QNN training dynamics is crucial for optimizing their performance, however, the role of quantum data in training for supervised learning such as classification and regression remains unclear. We reveal a quantum-data-driven dynamical transition where the target values and data determine the convergence of the training. Through analytical classification over the fixed points of the dynamical equation, we reveal a comprehensive `phase diagram' featuring seven distinct dynamics originating from a bifurcation with multiple codimension. Perturbative analyses identify both exponential and polynomial convergence class. We provide a non-perturbative theory to explain the transition via generalized restricted Haar ensemble. The analytical results are confirmed with numerical simulations and experimentation on IBM quantum devices. Our findings provide guidance on constructing the cost function to accelerate convergence in QNN training.

17+28 pages, 25 figures

References in corpus (26)

• Variational Quantum Algorithms
• 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
• Quantum computational chemistry
• Quantum Convolutional Neural Networks
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Chaos and complexity by design
• Quantum Optimization of Maximum Independent Set using Rydberg Atom Arrays
• Continuous-variable quantum neural networks
• Hierarchical quantum classifiers
• Experimental Realization of Quantum Artificial Intelligence
• Theory of overparametrization in quantum neural networks
• A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
• TensorCircuit: a Quantum Software Framework for the NISQ Era
• Universal discriminative quantum neural networks
• Representation Learning via Quantum Neural Tangent Kernels
• Analytic theory for the dynamics of wide quantum neural networks
• Quantum Neural Network Classifiers: A Tutorial
• Diagonal-unitary 2-designs and their implementations by quantum circuits
• Symmetric Pruning in Quantum Neural Networks
• Laziness, Barren Plateau, and Noise in Machine Learning
• Analyzing Convergence in Quantum Neural Networks: Deviations from Neural Tangent Kernels
• Dynamical transition in controllable quantum neural networks with large depth