We apply digitized Quantum Annealing (QA) and Quantum Approximate Optimization Algorithm (QAOA) to a paradigmatic task of supervised learning in artificial neural networks: the optimization of synaptic weights for the binary perceptron. At variance with the usual QAOA applications to MaxCut, or to quantum spin-chains ground state preparation, the classical is characterized by highly non-local multi-spin interactions. Yet, we provide evidence for the existence of optimal solutions for the QAOA parameters, which are among typical instances of the same problem, and we prove numerically an enhanced performance of QAOA over traditional QA. We also investigate on the role of the landscape geometry in this problem. \revision{By artificially breaking this geometrical structure, we show that the detrimental effect of a gap-closing transition, encountered in QA, is also negatively affecting the performance of our QAOA implementation.

Quantum approximate optimization algorithm applied to the binary perceptron

Baldassi, Carlo;Zecchina, Riccardo;
2023

Abstract

We apply digitized Quantum Annealing (QA) and Quantum Approximate Optimization Algorithm (QAOA) to a paradigmatic task of supervised learning in artificial neural networks: the optimization of synaptic weights for the binary perceptron. At variance with the usual QAOA applications to MaxCut, or to quantum spin-chains ground state preparation, the classical is characterized by highly non-local multi-spin interactions. Yet, we provide evidence for the existence of optimal solutions for the QAOA parameters, which are among typical instances of the same problem, and we prove numerically an enhanced performance of QAOA over traditional QA. We also investigate on the role of the landscape geometry in this problem. \revision{By artificially breaking this geometrical structure, we show that the detrimental effect of a gap-closing transition, encountered in QA, is also negatively affecting the performance of our QAOA implementation.
2023
2022
Torta, Pietro; Mbeng, Glen B.; Baldassi, Carlo; Zecchina, Riccardo; Santoro, Giuseppe E.
File in questo prodotto:
File Dimensione Formato  
2112.10219.pdf

accesso aperto

Descrizione: article
Tipologia: Documento in Pre-print (Pre-print document)
Licenza: PUBBLICO DOMINIO
Dimensione 745.68 kB
Formato Adobe PDF
745.68 kB 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/11565/4052527
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 6
  • ???jsp.display-item.citation.isi??? 5
social impact