Variational quantum tensor networks classifiers

Huang, Rui; Tan, Xiaoqing; Xu, Qingshan

doi:10.1016/j.neucom.2021.04.074

Cited by 33 publications

(11 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers are looking for ways to further improve QNNs performance. Variational quantum circuits inspired by TNs have been applied to machine learning [4][5][6][7][8][9] and optimization problems [10][11][12] in recent studies and have become one of the most effective architectures in quantum machine learning. The so-called TN is a framework that approximates higher-order tensors using the contraction of lower-order tensors, whose entanglement entropy satisfies the area law [13,14].…”

Section: Introductionmentioning

confidence: 99%

Transforming two-dimensional tensor networks into quantum circuits for supervised learning

Song,

Xu,

Zhou

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

There have been numerous quantum neural networks reported, but they struggle to match traditional neural networks in accuracy. Given the huge improvement of the neural network models’ accuracy by two-dimensional tensor network states in classical tensor network machine learning, it is promising to explore whether its application in quantum machine learning can extend the performance boundary of the models. Here, we transform two-dimensional tensor networks into quantum circuits for supervised learning. Specifically, we encode two-dimensional tensor networks into quantum circuits through rigorous mathematical proofs for constructing model ansätze, including string-bond states, entangled-plaquette states and isometric tensor network states. In addition, we propose adaptive data encoding methods and combine with tensor networks. We construct a tensor-network-inspired quantum circuit supervised learning framework for transferring tensor network machine learning from classical to quantum, and build several novel two-dimensional tensor network-inspired quantum classifiers based on this framework. Finally, we propose a parallel quantum machine learning method for multi-class classification to construct 2D TNQC-based multi-class classifiers. Classical simulation results on the MNIST benchmark dataset show that our proposed models achieve the state-of-the-art accuracy performance, significantly outperforming other quantum classifiers on both binary and multi-class classification tasks, and beat simple convolutional classifiers on a fair track with identical inputs. The noise resilience of the models makes them successfully run and work in a real quantum computer.

show abstract

Section: Introductionmentioning

confidence: 99%

Transforming two-dimensional tensor networks into quantum circuits for supervised learning

Song,

Xu,

Zhou

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Quantum superposition and entanglement render quantum computation a superior solution for processing large-scale data. Researchers have integrated quantum computation with machine learning, resulting in a series of quantum machine learning algorithms [1][2][3][4][5][6][7] applicable to discriminative 8,9 and generative learning 10,11 tasks. Tensor networks (TNs) extract features by contracting tensors, serving as crucial numerical tools for analyzing quantum multi-body systems.…”

Section: Introductionmentioning

confidence: 99%

A hybrid quantum-classical classification modelbased on branching multi-scale entanglementrenormalization ansatz

Hou,

Li,

et al. 2024

Preprint

View full text Add to dashboard Cite

Tensor networks are emerging architectures for implementing quantum classification models. Branching Multi-Scale Entanglement Renormalization Ansatz (BMERA) is a tensor network known for its enhanced entanglement properties. This paperintroduces a hybrid quantum-classical classification model based on BMERA and explores the correlation between circuit layout,expressiveness, and classification accuracy. Additionally, we introduce an autodifferentiation method for computing the costfunction gradient, which presents a viable option for other hybrid quantum-classical models. Through numerical experiments,we demonstrate the superior accuracy and robustness of our classification model in tasks such as image recognition andcluster excitation discrimination, outperforming quantum classification models based on tree tensor networks and multi-scaleentanglement regularization ansatz.

show abstract

“…Quantum computing is more computationally powerful than classical computing in solving specific problems, such as solving factorization, [1] equations, [2][3][4] dimensionality reduction, [5][6][7] anomaly detection, [8,9] classification, [10][11][12] and so on. [13][14][15] Recent works show that the quantum algorithm has a dramatic speedup on the cryptanalysis of symmetric crypto primitives.…”

Section: Introduction 1quantum Attacks Against Symmetric Crypto Primi...mentioning

confidence: 99%

Quantum Attacks on Type‐1 Generalized Feistel Schemes

et al. 2023

View full text Add to dashboard Cite

Generalized Feistel schemes (GFSs) are extremely important and extensively researched cryptographic schemes. In this paper, the security of Type‐1 GFS in quantum circumstances is investigated. On the one hand, in the qCCA setting, a new quantum polynomial‐time distinguisher on ‐round Type‐1 GFS with branches is given, which extends the previous results by rounds. This leads to a more efficient analysis of type‐1 GFS, that is, the complexity of some previous key‐recovery attacks is reduced by a factor of , where k is the key length of the internal round function. On the other hand, for CAST‐256, which is a certain block cipher based on Type‐1 GFS, a 17‐round quantum distinguisher in the qCPA setting is given. Based on this, an ‐round quantum key‐recovery attack with complexity is constructed.

show abstract

Variational quantum tensor networks classifiers

Cited by 33 publications

References 20 publications

Transforming two-dimensional tensor networks into quantum circuits for supervised learning

Transforming two-dimensional tensor networks into quantum circuits for supervised learning

A hybrid quantum-classical classification modelbased on branching multi-scale entanglementrenormalization ansatz

Quantum Attacks on Type‐1 Generalized Feistel Schemes

Contact Info

Product

Resources

About