On Adaptivity in Quantum Testing - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Transactions on Machine Learning Research Journal Année : 2023

On Adaptivity in Quantum Testing

Résumé

Can adaptive strategies outperform non-adaptive ones for quantum hypothesis selection? We exhibit problems where adaptive strategies provably reduce the number of required samples by a factor four in the worst case, and possibly more when the actual difficulty of the problem makes it possible. In addition, we exhibit specific hypotheses classes for which there is a provable polynomial separation between adaptive and non-adaptive strategies-a specificity of the quantum framework that does not appear in classical testing.
Fichier principal
Vignette du fichier
On_adaptivity.pdf (494.14 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04107265 , version 1 (26-05-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-04107265 , version 1

Citer

Omar Fawzi, Nicolas Flammarion, Aurélien Garivier, Aadil Oufkir. On Adaptivity in Quantum Testing. Transactions on Machine Learning Research Journal, 2023, pp.1-33. ⟨hal-04107265⟩
132 Consultations
118 Téléchargements

Partager

Gmail Facebook X LinkedIn More