The Quantum Path Kernel: a Generalized Quantum Neural Tangent Kernel for Deep Quantum Machine Learning

Abstract

Building a quantum analog of classical deep neural networks represents a fundamental challenge in quantum computing. A key issue is how to address the inherent non-linearity of classical deep learning, a problem in the quantum domain due to the fact that the composition of an arbitrary number of quantum gates, consisting of a series of sequential unitary transformations, is intrinsically linear. This problem has been variously approached in the literature, principally via the introduction of measurements between layers of unitary transformations. In this paper, we introduce the Quantum Path Kernel, a formulation of quantum machine learning capable of replicating those aspects of deep machine learning typically associated with superior generalization performance in the classical domain, specifically, hierarchical feature learning. Our approach generalizes the notion of Quantum Neural Tangent Kernel, which has been used to study the dynamics of classical and quantum machine learning models. The Quantum Path Kernel exploits the parameter trajectory, i.e. the curve delineated by model parameters as they evolve during training, enabling the representation of differential layer-wise convergence behaviors, or the formation of hierarchical parametric dependencies, in terms of their manifestation in the gradient space of the predictor function. We evaluate our approach with respect to variants of the classification of Gaussian XOR mixtures - an artificial but emblematic problem that intrinsically requires multilevel learning in order to achieve optimal class separation.

References in corpus (39)

• Barren plateaus in quantum neural network training landscapes
• Reconciling modern machine learning practice and the bias-variance trade-off
• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• An introduction to quantum machine learning
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• The power of quantum neural networks
• Power of data in quantum machine learning
• The quest for a Quantum Neural Network
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• A rigorous and robust quantum speed-up in supervised machine learning
• Quantum advantage in learning from experiments
• An initialization strategy for addressing barren plateaus in parametrized quantum circuits
• Layerwise learning for quantum neural networks
• An Artificial Neuron Implemented on an Actual Quantum Processor
• Nonlinear quantum mechanics implies polynomial-time solution for NP-complete and #P problems
• On Lazy Training in Differentiable Programming
• The Principles of Deep Learning Theory
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Quantum machine learning beyond kernel methods
• Trainability of Dissipative Perceptron-Based Quantum Neural Networks
• Theory of overparametrization in quantum neural networks
• Simulating a perceptron on a quantum computer
• Quantum Neuron: an elementary building block for machine learning on quantum computers
• The spectrum of kernel random matrices
• Representation Learning via Quantum Neural Tangent Kernels
• When Do Neural Networks Outperform Kernel Methods?
• Analytic theory for the dynamics of wide quantum neural networks
• Generalization despite overfitting in quantum machine learning models
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Every Model Learned by Gradient Descent Is Approximately a Kernel Machine
• On the linearity of large non-linear models: when and why the tangent kernel is constant
• A Simple Quantum Neural Net with a Periodic Activation Function
• Introducing Non-Linear Activations into Quantum Generative Models
• Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width
• Symmetric Pruning in Quantum Neural Networks
• Quantum Lazy Training
• High Dimensional Classification via Regularized and Unregularized Empirical Risk Minimization: Precise Error and Optimal Loss
• Towards Understanding Hierarchical Learning: Benefits of Neural Representations
• Nonlinear transformation of complex amplitudes via quantum singular value transformation

Cited by in corpus (4)

• Resource Saving via Ensemble Techniques for Quantum Neural Networks
• A Hyperparameter Study for Quantum Kernel Methods
• Generalization Bounds in Hybrid Quantum-Classical Machine Learning Models
• Kernel Reboot: Breaking the Boundaries of Neural Tangent Kernels for Neural Fields