Guardado en:
Detalles Bibliográficos
Autores principales: Sarkar, Ayana, Schnee, Martin, Radgohar, Roya, Fadaie, Mojde, Drouin-Touchette, Victor, Kourtis, Stefanos
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2508.10819
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912537850675200
author Sarkar, Ayana
Schnee, Martin
Radgohar, Roya
Fadaie, Mojde
Drouin-Touchette, Victor
Kourtis, Stefanos
author_facet Sarkar, Ayana
Schnee, Martin
Radgohar, Roya
Fadaie, Mojde
Drouin-Touchette, Victor
Kourtis, Stefanos
contents Quantum kernel methods (QKMs) offer an appealing framework for machine learning on near-term quantum computers. However, QKMs generically suffer from exponential concentration, requiring an exponential number of measurements to resolve the kernel values, with the exception of trivial (i.e., classically simulable) kernels. Here we propose a QKM that is free of exponential concentration, yet remains hard to simulate classically. Our QKM utilizes the weak ergodicity-breaking many-body dynamics in the Rydberg blockade of coherently driven neutral atom arrays. We demonstrate the fundamental properties of our QKM by analytically solving an approximate toy model of its underpinning quantum dynamics, as well as by extensive numerical simulations on randomly generated datasets. We further show that the proposed kernel exhibits effective learning on real data. The proposed QKM can be implemented in current neutral atom quantum computers.
format Preprint
id arxiv_https___arxiv_org_abs_2508_10819
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Concentration-Free Quantum Kernel Learning in the Rydberg Blockade
Sarkar, Ayana
Schnee, Martin
Radgohar, Roya
Fadaie, Mojde
Drouin-Touchette, Victor
Kourtis, Stefanos
Strongly Correlated Electrons
Quantum Physics
Quantum kernel methods (QKMs) offer an appealing framework for machine learning on near-term quantum computers. However, QKMs generically suffer from exponential concentration, requiring an exponential number of measurements to resolve the kernel values, with the exception of trivial (i.e., classically simulable) kernels. Here we propose a QKM that is free of exponential concentration, yet remains hard to simulate classically. Our QKM utilizes the weak ergodicity-breaking many-body dynamics in the Rydberg blockade of coherently driven neutral atom arrays. We demonstrate the fundamental properties of our QKM by analytically solving an approximate toy model of its underpinning quantum dynamics, as well as by extensive numerical simulations on randomly generated datasets. We further show that the proposed kernel exhibits effective learning on real data. The proposed QKM can be implemented in current neutral atom quantum computers.
title Concentration-Free Quantum Kernel Learning in the Rydberg Blockade
topic Strongly Correlated Electrons
Quantum Physics
url https://arxiv.org/abs/2508.10819