Quantifying how far the output of a learning algorithm is from its target is an essential task in machine learning. However, in quantum settings, the loss landscapes of commonly used distance metrics often produce undesirable outcomes such as poor local minima and exponentially decaying gradients. To overcome these obstacles, we consider here the recently proposed quantum earth mover's (EM) or Wasserstein-1 distance as a quantum analog to the classical EM distance. We show that the quantum EM distance possesses unique properties, not found in other commonly used quantum distance metrics, that make quantum learning more stable and efficient. We propose a quantum Wasserstein generative adversarial network (qWGAN) which takes advantage of the quantum EM distance and provides an efficient means of performing learning on quantum data. We provide examples where our qWGAN is capable of learning a diverse set of quantum data with only resources polynomial in the number of qubits.

Learning quantum data with the quantum earth mover’s distance / Kiani, Bobak Toussi; De Palma, Giacomo; Marvian, Milad; Liu, Zi-Wen; Lloyd, Seth. - In: QUANTUM SCIENCE AND TECHNOLOGY. - ISSN 2058-9565. - ELETTRONICO. - 7:4(2022), pp. 045002.1-045002.28. [10.1088/2058-9565/ac79c9]

Learning quantum data with the quantum earth mover’s distance

De Palma, Giacomo;
2022

Abstract

Quantifying how far the output of a learning algorithm is from its target is an essential task in machine learning. However, in quantum settings, the loss landscapes of commonly used distance metrics often produce undesirable outcomes such as poor local minima and exponentially decaying gradients. To overcome these obstacles, we consider here the recently proposed quantum earth mover's (EM) or Wasserstein-1 distance as a quantum analog to the classical EM distance. We show that the quantum EM distance possesses unique properties, not found in other commonly used quantum distance metrics, that make quantum learning more stable and efficient. We propose a quantum Wasserstein generative adversarial network (qWGAN) which takes advantage of the quantum EM distance and provides an efficient means of performing learning on quantum data. We provide examples where our qWGAN is capable of learning a diverse set of quantum data with only resources polynomial in the number of qubits.
2022
Learning quantum data with the quantum earth mover’s distance / Kiani, Bobak Toussi; De Palma, Giacomo; Marvian, Milad; Liu, Zi-Wen; Lloyd, Seth. - In: QUANTUM SCIENCE AND TECHNOLOGY. - ISSN 2058-9565. - ELETTRONICO. - 7:4(2022), pp. 045002.1-045002.28. [10.1088/2058-9565/ac79c9]
Kiani, Bobak Toussi; De Palma, Giacomo; Marvian, Milad; Liu, Zi-Wen; Lloyd, Seth
File in questo prodotto:
File Dimensione Formato  
Learning quantum data with the quantum earth mover's distance.pdf

accesso aperto

Tipo: Versione (PDF) editoriale
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 16.17 MB
Formato Adobe PDF
16.17 MB Adobe PDF Visualizza/Apri

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/11585/890054
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 16
  • ???jsp.display-item.citation.isi??? 14
social impact