Quantum learning without quantum memory
Sentís Herrera, Gael (Universitat Autònoma de Barcelona. Departament de Física)
Calsamiglia Costa, John (Universitat Autònoma de Barcelona. Departament de Física)
Muñoz Tapia, Ramon (Universitat Autònoma de Barcelona. Departament de Física)
Bagán Capella, Emili (Universitat Autònoma de Barcelona. Departament de Física)

Date:	2012
Abstract:	A quantum learning machine for binary classification of qubit states that does not require quantum memory is introduced and shown to perform with the minimum error rate allowed by quantum mechanics for any size of the training set. This result is shown to be robust under (an arbitrary amount of) noise and under (statistical) variations in the composition of the training set, provided it is large enough. This machine can be used an arbitrary number of times without retraining. Its required classical memory grows only logarithmically with the number of training qubits, while its excess risk decreases as the inverse of this number, and twice as fast as the excess risk of an "estimate-and-discriminate" machine, which estimates the states of the training qubits and classifies the data qubit with a discrimination protocol tailored to the obtained estimates.
Rights:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la comunicació pública de l'obra i la creació d'obres derivades, sempre que no sigui amb finalitats comercials i que es distribueixin sota la mateixa llicència que regula l'obra original. Cal que es reconegui l'autoria de l'obra original.
Language:	Anglès
Document:	Article ; Versió publicada
Subject:	Òptica quàntica ; Quantum optics ; Statistics information theory and computation ; Quantum physics
Published in:	Scientific reports, Vol. 2, art. 708 (October 2012) , ISSN 2045-2322

DOI: 10.1038/srep00708
PMID: 23050092

8 p, 354.7 KB

The record appears in these collections:
Articles > Published articles