Quantum machine learning in feature Hilbert spaces
read the original abstract
The basic idea of quantum computing is surprisingly similar to that of kernel methods in machine learning, namely to efficiently perform computations in an intractably large Hilbert space. In this paper we explore some theoretical foundations of this link and show how it opens up a new avenue for the design of quantum machine learning algorithms. We interpret the process of encoding inputs in a quantum state as a nonlinear feature map that maps data to quantum Hilbert space. A quantum computer can now analyse the input data in this feature space. Based on this link, we discuss two approaches for building a quantum model for classification. In the first approach, the quantum device estimates inner products of quantum states to compute a classically intractable kernel. This kernel can be fed into any classical kernel method such as a support vector machine. In the second approach, we can use a variational quantum circuit as a linear model that classifies data explicitly in Hilbert space. We illustrate these ideas with a feature map based on squeezing in a continuous-variable system, and visualise the working principle with $2$-dimensional mini-benchmark datasets.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
PennyLane: Automatic differentiation of hybrid quantum-classical computations
PennyLane is a software library extending automatic differentiation to hybrid quantum-classical systems for variational quantum algorithms.
-
Frustration-Induced Expressibility Limitations in Variational Quantum Algorithms
Geometric frustration in a square-lattice Ising model with diagonal couplings produces strongly inhomogeneous correlations that standard Hamiltonian-inspired variational ansatze cannot capture efficiently, increasing ...
-
Kernel Alignment for Quantum Support Vector Machines Using Genetic Algorithms
Genetic algorithm optimization of QSVM kernel circuits produces encodings that match or exceed standard classical and quantum kernels on binary and multi-class datasets, with a reported positive correlation to kernel entropy.
-
Benchmarking a machine-learning differential equations solver on a neutral-atom logical processor
Logical quantum kernels outperform physical ones when solving differential equations on a neutral-atom processor, with gains traced to noise error detection in the logical encoding.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.