Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Xinyi, Hazan, Elad, Li, Tongyang, Lu, Zhou, Wang, Xinzhao, Yang, Rui
Format: Preprint
Veröffentlicht: 2022
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2206.00220
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910607513485312
author Chen, Xinyi
Hazan, Elad
Li, Tongyang
Lu, Zhou
Wang, Xinzhao
Yang, Rui
author_facet Chen, Xinyi
Hazan, Elad
Li, Tongyang
Lu, Zhou
Wang, Xinzhao
Yang, Rui
contents The problem of efficient quantum state learning, also called shadow tomography, aims to comprehend an unknown $d$-dimensional quantum state through POVMs. Yet, these states are rarely static; they evolve due to factors such as measurements, environmental noise, or inherent Hamiltonian state transitions. This paper leverages techniques from adaptive online learning to keep pace with such state changes. The key metrics considered for learning in these mutable environments are enhanced notions of regret, specifically adaptive and dynamic regret. We present adaptive and dynamic regret bounds for online shadow tomography, which are polynomial in the number of qubits and sublinear in the number of measurements. To support our theoretical findings, we include numerical experiments that validate our proposed models.
format Preprint
id arxiv_https___arxiv_org_abs_2206_00220
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Adaptive Online Learning of Quantum States
Chen, Xinyi
Hazan, Elad
Li, Tongyang
Lu, Zhou
Wang, Xinzhao
Yang, Rui
Machine Learning
Quantum Physics
The problem of efficient quantum state learning, also called shadow tomography, aims to comprehend an unknown $d$-dimensional quantum state through POVMs. Yet, these states are rarely static; they evolve due to factors such as measurements, environmental noise, or inherent Hamiltonian state transitions. This paper leverages techniques from adaptive online learning to keep pace with such state changes. The key metrics considered for learning in these mutable environments are enhanced notions of regret, specifically adaptive and dynamic regret. We present adaptive and dynamic regret bounds for online shadow tomography, which are polynomial in the number of qubits and sublinear in the number of measurements. To support our theoretical findings, we include numerical experiments that validate our proposed models.
title Adaptive Online Learning of Quantum States
topic Machine Learning
Quantum Physics
url https://arxiv.org/abs/2206.00220