Quantum kernels with squeezed-state encoding for machine learning
arXiv:2108.11114 · doi:10.1016/j.physleta.2022.128088
Abstract
Kernel methods are powerful for machine learning, as they can represent data in feature spaces that similarities between samples may be faithfully captured. Recently, it is realized that machine learning enhanced by quantum computing is closely related to kernel methods, where the exponentially large Hilbert space turns to be a feature space more expressive than classical ones. In this paper, we generalize quantum kernel methods by encoding data into continuous-variable quantum states, which can benefit from the infinite-dimensional Hilbert space of continuous variables. Specially, we propose squeezed-state encoding, in which data is encoded as either in the amplitude or the phase. The kernels can be calculated on a quantum computer and then are combined with classical machine learning, e.g. support vector machine, for training and predicting tasks. Their comparisons with other classical kernels are also addressed. Lastly, we discuss physical implementations of squeezed-state encoding for machine learning in quantum platforms such as trapped ions.
arXiv comment5 pages, 4 figures
References in corpus (24)
- Scikit-learn: Machine Learning in Python
- Quantum Machine Learning
- Gaussian Quantum Information
- Quantum algorithm for solving linear systems of equations
- Supervised learning with quantum enhanced feature spaces
- Quantum support vector machine for big data classification
- Quantum machine learning in feature Hilbert spaces
- Quantum Circuit Learning
- Quantum principal component analysis
- Quantum computing with trapped ions
- The effect of data encoding on the expressive power of variational quantum machine learning models
- Data re-uploading for a universal quantum classifier
- Quantum generative adversarial learning
- Quantum Data Fitting
- Quantum-enhanced machine learning
- Continuous-variable quantum neural networks
- Encoding a qubit in a trapped-ion mechanical oscillator
- Supervised quantum machine learning models are kernel methods
- Quantum machine learning over infinite dimensions
- Experimental Preparation of High NOON States for Phonons
- Universal Approximation Property of Quantum Machine Learning Models in Quantum-Enhanced Feature Spaces
- Continuous variables quantum computation over the vibrational modes of a single trapped ion
- Protocol for implementing quantum nonparametric learning with trapped ions
- Realizing quantum linear regression with auxiliary qumodes
Cited by in corpus (5)
- Continuous-variable quantum kernel method on a programmable photonic quantum processor
- Optimal Qubit Mapping Search for Encoding Classical Data into Matrix Product State Representation with Minimal Loss
- Variable Hyperparameterized Gaussian Kernel using Displaced Squeezed Vacuum State
- Quantum fidelity kernel with a trapped-ion simulation platform
- Towards Continuous-variable Quantum Neural Networks for Biomedical Imaging