Quantum bandits

Autor: Giuseppe, Di Molfetta, Casalé, Balthazar, Di Molfetta, Giuseppe, Kadri, Hachem, Ralaivola, Liva
Přispěvatelé: Laboratoire d'Informatique et Systèmes (LIS), Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS), éQuipe d'AppRentissage de MArseille (QARMA), Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS), Calcul Naturel (CANA), Criteo AI Lab, Criteo [Paris], ANR-19-CE23-0011,QuantML,Apprentissage automatique quantique : fondements théoriques et algorithmes(2019), Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU), Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU)
Jazyk: angličtina
Rok vydání: 2020
Předmět:
FOS: Computer and information sciences
Computer Science - Machine Learning
Computer Science - Artificial Intelligence
Computer science
FOS: Physical sciences
Machine Learning (stat.ML)
02 engineering and technology
Quantum modeling
01 natural sciences
Machine Learning (cs.LG)
Theoretical Computer Science
Amplitude amplification
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]
[STAT.ML]Statistics [stat]/Machine Learning [stat.ML]
[PHYS.QPHY]Physics [physics]/Quantum Physics [quant-ph]
Statistics - Machine Learning
Artificial Intelligence
0103 physical sciences
0202 electrical engineering
electronic engineering
information engineering
010306 general physics
Quantum
ComputingMilieux_MISCELLANEOUS
Quadratic growth
Quantum Physics
Applied Mathematics
TheoryofComputation_GENERAL
Identification (information)
Artificial Intelligence (cs.AI)
Computational Theory and Mathematics
020201 artificial intelligence & image processing
Quantum Physics (quant-ph)
Algorithm
Software
Zdroj: Quantum Machine Intelligence
Quantum Machine Intelligence, 2020, 2 (1), ⟨10.1007/s42484-020-00024-8⟩
Quantum Machine Intelligence, 2020, 2 (1), pp.11. ⟨10.1007/s42484-020-00024-8⟩
ISSN: 2524-4906
DOI: 10.1007/s42484-020-00024-8⟩
Popis: We consider the quantum version of the bandit problem known as {\em best arm identification} (BAI). We first propose a quantum modeling of the BAI problem, which assumes that both the learning agent and the environment are quantum; we then propose an algorithm based on quantum amplitude amplification to solve BAI. We formally analyze the behavior of the algorithm on all instances of the problem and we show, in particular, that it is able to get the optimal solution quadratically faster than what is known to hold in the classical case.
All your comments are very welcome!
Databáze: OpenAIRE
Externí odkaz: