Work

Expressivity vs. Generalization in Quantum Kernel Methods

Year: 2025

Type: conference-paper

Abstract: We analytically and numerically investigate the expressivity and generalization ability of quantum kernel models.We consider prototypical parallel encoding strategies and show that they give rise to simple universal forms of quantum kernels.By using qubit-dependent data rescaling schemes, we can exponentially vary the spectral content of the kernel and thereby control its simplicity bias.We obtain analytical results on the kernel eigenspectrum and connect it to theories of kernel generalization, which allow us to study the influence of expressivity on generalization error.

Source: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)

DOI: 10.14428/esann/2025.es2025-152

Authors: Markus Gross, Markus Lange, Bogusz Bujnowski, Hans-Martin Rieser

Institution: Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)

Language: English

Topic: Quantum Computing Algorithms and Architecture

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

OpenAlex ID: W4409455387

FWCI: 1.006

Cites: 6

Cited by: 1

Related to: 10