On the Design of Expressive and Trainable Pulse-based Quantum Machine Learning Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Tao, Han-Xiao, Wang, Xin, Wu, Re-Bing
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908637186752512
author Tao, Han-Xiao
Wang, Xin
Wu, Re-Bing
author_facet Tao, Han-Xiao
Wang, Xin
Wu, Re-Bing
contents Pulse-based Quantum Machine Learning (QML) has emerged as a novel paradigm in quantum artificial intelligence due to its exceptional hardware efficiency. For practical applications, pulse-based models must be both expressive and trainable. Previous studies suggest that pulse-based models under dynamic symmetry can be effectively trained, thanks to a favorable loss landscape that avoids barren plateaus. However, the resulting uncontrollability may compromise expressivity when the model is inadequately designed. This paper investigates the requirements for pulse-based QML models to be expressive while preserving trainability. We establish a necessary condition pertaining to the system's initial state, the measurement observable, and the underlying dynamical symmetry Lie algebra, supported by numerical simulations. Our findings provide a framework for designing practical pulse-based QML models that balance expressivity and trainability.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05559
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the Design of Expressive and Trainable Pulse-based Quantum Machine Learning Models
Tao, Han-Xiao
Wang, Xin
Wu, Re-Bing
Quantum Physics
Machine Learning
Pulse-based Quantum Machine Learning (QML) has emerged as a novel paradigm in quantum artificial intelligence due to its exceptional hardware efficiency. For practical applications, pulse-based models must be both expressive and trainable. Previous studies suggest that pulse-based models under dynamic symmetry can be effectively trained, thanks to a favorable loss landscape that avoids barren plateaus. However, the resulting uncontrollability may compromise expressivity when the model is inadequately designed. This paper investigates the requirements for pulse-based QML models to be expressive while preserving trainability. We establish a necessary condition pertaining to the system's initial state, the measurement observable, and the underlying dynamical symmetry Lie algebra, supported by numerical simulations. Our findings provide a framework for designing practical pulse-based QML models that balance expressivity and trainability.
title On the Design of Expressive and Trainable Pulse-based Quantum Machine Learning Models
topic Quantum Physics
Machine Learning
url https://arxiv.org/abs/2508.05559