Learning to generate high-dimensional distributions with low-dimensional quantum Boltzmann machines

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tüysüz, Cenk, Demidik, Maria, Coopmans, Luuk, Rinaldi, Enrico, Croft, Vincent, Haddad, Yacine, Rosenkranz, Matthias, Jansen, Karl
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917812330561536
author Tüysüz, Cenk
Demidik, Maria
Coopmans, Luuk
Rinaldi, Enrico
Croft, Vincent
Haddad, Yacine
Rosenkranz, Matthias
Jansen, Karl
author_facet Tüysüz, Cenk
Demidik, Maria
Coopmans, Luuk
Rinaldi, Enrico
Croft, Vincent
Haddad, Yacine
Rosenkranz, Matthias
Jansen, Karl
contents In recent years, researchers have been exploring ways to generalize Boltzmann machines (BMs) to quantum systems, leading to the development of variations such as fully-visible and restricted quantum Boltzmann machines (QBMs). Due to the non-commuting nature of their Hamiltonians, restricted QBMs face trainability issues, whereas fully-visible QBMs have emerged as a more tractable option, as recent results demonstrate their sample-efficient trainability. These results position fully-visible QBMs as a favorable choice, offering potential improvements over fully-visible BMs without suffering from the trainability issues associated with restricted QBMs. In this work, we show that low-dimensional, fully-visible QBMs can learn to generate distributions typically associated with higher-dimensional systems. We validate our findings through numerical experiments on both artificial datasets and real-world examples from the high energy physics problem of jet event generation. We find that non-commuting terms and Hamiltonian connectivity improve the learning capabilities of QBMs, providing flexible resources suitable for various hardware architectures. Furthermore, we provide strategies and future directions to maximize the learning capacity of fully-visible QBMs.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16363
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning to generate high-dimensional distributions with low-dimensional quantum Boltzmann machines
Tüysüz, Cenk
Demidik, Maria
Coopmans, Luuk
Rinaldi, Enrico
Croft, Vincent
Haddad, Yacine
Rosenkranz, Matthias
Jansen, Karl
Quantum Physics
Computational Physics
In recent years, researchers have been exploring ways to generalize Boltzmann machines (BMs) to quantum systems, leading to the development of variations such as fully-visible and restricted quantum Boltzmann machines (QBMs). Due to the non-commuting nature of their Hamiltonians, restricted QBMs face trainability issues, whereas fully-visible QBMs have emerged as a more tractable option, as recent results demonstrate their sample-efficient trainability. These results position fully-visible QBMs as a favorable choice, offering potential improvements over fully-visible BMs without suffering from the trainability issues associated with restricted QBMs. In this work, we show that low-dimensional, fully-visible QBMs can learn to generate distributions typically associated with higher-dimensional systems. We validate our findings through numerical experiments on both artificial datasets and real-world examples from the high energy physics problem of jet event generation. We find that non-commuting terms and Hamiltonian connectivity improve the learning capabilities of QBMs, providing flexible resources suitable for various hardware architectures. Furthermore, we provide strategies and future directions to maximize the learning capacity of fully-visible QBMs.
title Learning to generate high-dimensional distributions with low-dimensional quantum Boltzmann machines
topic Quantum Physics
Computational Physics
url https://arxiv.org/abs/2410.16363