Quantum machine learning promises to revolutionize traditional machine learning by efficiently addressing hard tasks for classical computation. While claims of quantum speed-up have been announced for gate-based quantum computers and photon-based boson samplers, demonstration of an advantage by adiabatic quantum annealers (AQAs) is open. Here we quantify the computational cost and the performance of restricted Boltzmann machines (RBMs), a widely investigated machine learning model, by classical and quantum annealing. Despite the lower computational complexity of the quantum RBM being lost due to physical implementation overheads, a quantum speed-up may arise as a reduction by orders of magnitude of the computational time. By employing real-world cybersecurity datasets, we observe that the negative phase on sufficiently challenging tasks is computed up to 64 times faster by AQAs during the exploitation phase. Therefore, although a quantum speed-up highly depends on the problem’s characteristics, it emerges in existing hardware on real-world data.

Anomaly detection speed-up by quantum restricted Boltzmann machines / L. Moro, E. Prati. - In: COMMUNICATIONS PHYSICS. - ISSN 2399-3650. - 6:1(2023), pp. 269.1-269.10. [10.1038/s42005-023-01390-y]

Anomaly detection speed-up by quantum restricted Boltzmann machines

E. Prati
Ultimo
2023

Abstract

Quantum machine learning promises to revolutionize traditional machine learning by efficiently addressing hard tasks for classical computation. While claims of quantum speed-up have been announced for gate-based quantum computers and photon-based boson samplers, demonstration of an advantage by adiabatic quantum annealers (AQAs) is open. Here we quantify the computational cost and the performance of restricted Boltzmann machines (RBMs), a widely investigated machine learning model, by classical and quantum annealing. Despite the lower computational complexity of the quantum RBM being lost due to physical implementation overheads, a quantum speed-up may arise as a reduction by orders of magnitude of the computational time. By employing real-world cybersecurity datasets, we observe that the negative phase on sufficiently challenging tasks is computed up to 64 times faster by AQAs during the exploitation phase. Therefore, although a quantum speed-up highly depends on the problem’s characteristics, it emerges in existing hardware on real-world data.
Settore FIS/03 - Fisica della Materia
Settore FIS/02 - Fisica Teorica, Modelli e Metodi Matematici
   Piano di Sostegno alla Ricerca 2015-2017 - Linea 2 "Dotazione annuale per attività istituzionali" (anno 2021)
   UNIVERSITA' DEGLI STUDI DI MILANO
2023
23-set-2023
Article (author)
File in questo prodotto:
File Dimensione Formato  
s42005-021-00684-3-1.pdf

accesso aperto

Tipologia: Publisher's version/PDF
Dimensione 4.16 MB
Formato Adobe PDF
4.16 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/1005308
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact