Barren plateaus in quantum neural network training landscapes

Gradient-based hybrid quantum-classical algorithms are often initialised with random, unstructured guesses. Here, the authors show that this approach will fail in the long run, due to the exponentially-small probability of finding a large enough gradient along any direction.

Guardado en:

Detalles Bibliográficos
Autores principales:	Jarrod R. McClean, Sergio Boixo, Vadim N. Smelyanskiy, Ryan Babbush, Hartmut Neven
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2018
Materias:	Science Q
Acceso en línea:	https://doaj.org/article/2d565792ea6b4691bd7767c8d897c439
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2d565792ea6b4691bd7767c8d897c439
record_format	dspace
spelling	oai:doaj.org-article:2d565792ea6b4691bd7767c8d897c4392021-12-02T14:40:31ZBarren plateaus in quantum neural network training landscapes10.1038/s41467-018-07090-42041-1723https://doaj.org/article/2d565792ea6b4691bd7767c8d897c4392018-11-01T00:00:00Zhttps://doi.org/10.1038/s41467-018-07090-4https://doaj.org/toc/2041-1723Gradient-based hybrid quantum-classical algorithms are often initialised with random, unstructured guesses. Here, the authors show that this approach will fail in the long run, due to the exponentially-small probability of finding a large enough gradient along any direction.Jarrod R. McCleanSergio BoixoVadim N. SmelyanskiyRyan BabbushHartmut NevenNature PortfolioarticleScienceQENNature Communications, Vol 9, Iss 1, Pp 1-6 (2018)
institution	DOAJ
collection	DOAJ
language	EN
topic	Science Q
spellingShingle	Science Q Jarrod R. McClean Sergio Boixo Vadim N. Smelyanskiy Ryan Babbush Hartmut Neven Barren plateaus in quantum neural network training landscapes
description	Gradient-based hybrid quantum-classical algorithms are often initialised with random, unstructured guesses. Here, the authors show that this approach will fail in the long run, due to the exponentially-small probability of finding a large enough gradient along any direction.
format	article
author	Jarrod R. McClean Sergio Boixo Vadim N. Smelyanskiy Ryan Babbush Hartmut Neven
author_facet	Jarrod R. McClean Sergio Boixo Vadim N. Smelyanskiy Ryan Babbush Hartmut Neven
author_sort	Jarrod R. McClean
title	Barren plateaus in quantum neural network training landscapes
title_short	Barren plateaus in quantum neural network training landscapes
title_full	Barren plateaus in quantum neural network training landscapes
title_fullStr	Barren plateaus in quantum neural network training landscapes
title_full_unstemmed	Barren plateaus in quantum neural network training landscapes
title_sort	barren plateaus in quantum neural network training landscapes
publisher	Nature Portfolio
publishDate	2018
url	https://doaj.org/article/2d565792ea6b4691bd7767c8d897c439
work_keys_str_mv	AT jarrodrmcclean barrenplateausinquantumneuralnetworktraininglandscapes AT sergioboixo barrenplateausinquantumneuralnetworktraininglandscapes AT vadimnsmelyanskiy barrenplateausinquantumneuralnetworktraininglandscapes AT ryanbabbush barrenplateausinquantumneuralnetworktraininglandscapes AT hartmutneven barrenplateausinquantumneuralnetworktraininglandscapes
_version_	1718390225752817664

Barren plateaus in quantum neural network training landscapes

Ejemplares similares