Neural quantum kernels: training quantum kernels with quantum neural networks
arXiv:2401.04642 · doi:10.1103/xphb-x2g4
Abstract
Quantum and classical machine learning have been naturally connected through kernel methods, which have also served as proof-of-concept for quantum advantage. Quantum embeddings encode classical data into quantum feature states, enabling the construction of embedding quantum kernels (EQKs) by measuring vector similarities and projected quantum kernels (PQKs) through projections of these states. However, in both approaches, the model is influenced by the choice of the embedding. In this work, we propose using the training of a quantum neural network (QNN) to construct neural quantum kernels: both neural EQKs and neural PQKs, which are problem-inspired kernels. Unlike previous methods in the literature, our approach requires the kernel matrix to be constructed only once. We present several strategies for constructing neural quantum kernels and propose a scalable method to train an -qubit data re-uploading quantum neural network (QNN). We provide numerical evidence of the performance of these models under noisy conditions. Additionally, we demonstrate how neural quantum kernels can alleviate exponential concentration and enhance generalization capabilities compared to problem-agnostic kernels, positioning them as a scalable and robust solution for quantum machine learning applications.
References in corpus (40)
- Quantum Machine Learning
- Supervised learning with quantum enhanced feature spaces
- Machine learning and the physical sciences
- Barren plateaus in quantum neural network training landscapes
- Quantum support vector machine for big data classification
- Quantum machine learning in feature Hilbert spaces
- Parameterized quantum circuits as machine learning models
- Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
- Circuit-centric quantum classifiers
- The effect of data encoding on the expressive power of variational quantum machine learning models
- Power of data in quantum machine learning
- Data re-uploading for a universal quantum classifier
- Connecting ansatz expressibility to gradient magnitudes and barren plateaus
- A rigorous and robust quantum speed-up in supervised machine learning
- Learning the quantum algorithm for state overlap
- Barren Plateaus in Variational Quantum Computing
- Quantum machine learning beyond kernel methods
- Quantum agents in the Gym: a variational quantum algorithm for deep Q-learning
- Exploiting symmetry in variational quantum machine learning
- Group-Invariant Quantum Machine Learning
- Training Quantum Embedding Kernels on Near-Term Quantum Computers
- A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
- On the Quantum versus Classical Learnability of Discrete Distributions
- Understanding quantum machine learning also requires rethinking generalization
- One qubit as a Universal Approximant
- Beyond the swap test: optimal estimation of quantum state overlap
- Covariant quantum kernels for data with group structure
- Experimental quantum kernel machine learning with nuclear spins in a solid
- Quantum enhancements for deep reinforcement learning in large spaces
- Building spatial symmetries into parameterized quantum circuits for faster training
- Quantum algorithms: A survey of applications and end-to-end complexities
- Quantum anomaly detection in the latent space of proton collision events at the LHC
- Quantum Phase Recognition via Quantum Kernel Methods
- Variational Quantum Approximate Support Vector Machine with Inference Transfer
- Multidimensional Fourier series with quantum circuits
- On the expressivity of embedding quantum kernels
- A super-polynomial quantum-classical separation for density modelling
- Demonstration of a bosonic quantum classifier with data re-uploading
- Satellite image classification with neural quantum kernels
- Gradients and frequency profiles of quantum re-uploading models