Quantum Vision Transformers for Quark–Gluon Classification - INSPIRE

DataBETA

Quantum Vision Transformers for Quark–Gluon Classification

Marçal Comajoan Cara
(
- Vigo U.
)
,
Gopal Ramesh Dahale
(
- Indian Inst. Tech., Bhilai
)
,
Zhongtian Dong
(
- Kansas U.
)
,
Roy T. Forestano
(
- Florida U.
)
,
Sergei Gleyzer
(
- Alabama U.
)

May 13, 2024

14 pages

Published in:

Axioms 13 (2024) 5, 323,
Axioms 13 (2024) 323

Published: May 13, 2024

e-Print:

2405.10284 [quant-ph]

DOI:

10.3390/axioms13050323

View in:

ADS Abstract Service

reference search4 citations

Citations per year

Abstract: (MDPI)

We introduce a hybrid quantum-classical vision transformer architecture, notable for its integration of variational quantum circuits within both the attention mechanism and the multi-layer perceptrons. The research addresses the critical challenge of computational efficiency and resource constraints in analyzing data from the upcoming High Luminosity Large Hadron Collider, presenting the architecture as a potential solution. In particular, we evaluate our method by applying the model to multi-detector jet images from CMS Open Data. The goal is to distinguish quark-initiated from gluon-initiated jets. We successfully train the quantum model and evaluate it via numerical simulations. Using this approach, we achieve classification performance almost on par with the one obtained with the completely classical architecture, considering a similar number of parameters.

Note:

14 pages, 8 figures. Published in MDPI Axioms 2024, 13(5), 323

quantum computing
deep learning
quantum machine learning
classical-quantum neural networks
vision transformers
supervised learning
classification
Large Hadron Collider
68Q12
81P68

References(69)

Figures(6)

[1]

The HL-LHC Project

[2]

Challenges in Monte Carlo Event Generator Software for High-Luminosity LHC

HSF Physics Event Generator WG

Collaboration

•

Andrea Valassi
(
- CERN
)
(ed.)

et al.

- Comput.Softw.Big Sci. 5 (2021) 1, 12
•
e-Print:
- 2004.13687
•
DOI:
- 10.1007/s41781-021-00055-1

Guest Column: A Survey of Quantum Learning Theory

- Sigact News (2017) 41-67
•
e-Print:
- 1701.06806
•
DOI:
- 10.1145/3106700.3106710

[4]

Quantum machine learning

Jacob Biamonte
(
- Skoltech and
- Waterloo U.
)
,
Peter Wittek
(
- ICFO, Barcelona
)
,
Nicola Pancotti
(
- Munich, Max Planck Inst. Quantenopt.
)
,
Patrick Rebentrost
(
- MIT
)
,
Nathan Wiebe
(
- Microsoft, Redmond
)

et al.

- Nature 549 (2017) 7671, 195-202
•
e-Print:
- 1611.09347
•
DOI:
- 10.1038/nature23474

[5]

Quantum Machine Learning in Feature Hilbert Spaces

Maria Schuld
(
- Unlisted, CA
)
,
Nathan Killoran
(
- Unlisted, CA
)

- Phys.Rev.Lett. 122 (2019) 4, 040504
•
DOI:
- 10.1103/PhysRevLett.122.040504

[6]

Quantum computing models for artificial neural networks

C. Macchiavello
(
- Pavia U.
)
,
D. Bajoni
(
- Pavia U.
)
,
D. Gerace
(
- IBM, Zurich
)
,
F. Tacchino
(
- INFN, Pavia and
- Pavia U.
)
,
S. Mangini
(
- Pavia U.
)

- EPL 134 (2021) 1, 10002
•
DOI:
- 10.1209/0295-5075/134/10002

[7]

A rigorous and robust quantum speed-up in supervised machine learning

- Nature Phys. 17 (2021) 9, 1013-1017
•
e-Print:
- 2010.02174
•
DOI:
- 10.1038/s41567-021-01287-z

[8]

Quantum advantage in learning from experiments

Hsin-Yuan Huang
(
- Caltech and
- Caltech, IQI
)
,
Michael Broughton
(
- Unlisted, US, CA
)
,
Jordan Cotler
(
- Unlisted, US, MA
)
,
Sitan Chen
(
- UC, Berkeley (main)
)
,
Jerry Li
(
- Microsoft, Redmond
)

et al.

- Science 376 (2022) 6598, abn7293
•
e-Print:
- 2112.00778
•
DOI:
- 10.1126/science.abn7293

[9]

Generalization in quantum machine learning from few training data

Matthias C. Caro
(
- Munich, Tech. U. and
- MCQST, Munich
)
,
Hsin-Yuan Huang
(
- Caltech and
- Caltech, IQI
)
,
M. Cerezo
(
- Los Alamos
)
,
Kunal Sharma
(
- Maryland U., College Park
)
,
Andrew Sornborger
(
- Los Alamos and
- Oak Ridge
)

et al.

- Nature Commun. 13 (2022) 1, 4919
•
e-Print:
- 2111.05292
•
DOI:
- 10.1038/s41467-022-32550-3

[10]

$\mathbb{Z}_2\times \mathbb{Z}_2$ Equivariant Quantum Neural Networks: Benchmarking against Classical Neural Networks

Zhongtian Dong
(
- Kansas U.
)
,
Marçal Comajoan Cara
(
- Vigo U.
)
,
Gopal Ramesh Dahale
(
- Indian Inst. Tech., Bhilai
)
,
Roy T. Forestano
(
- Florida U.
)
,
Sergei Gleyzer
(
- Alabama U.
)

et al.

- Axioms 13 (2024) 3, 188
•
e-Print:
- 2311.18744
•
DOI:
- 10.3390/axioms13030188

[11]

A Comparison between Invariant and Equivariant Classical and Quantum Graph Neural Networks

Roy T. Forestano
(
- Florida U.
)
,
Marçal Comajoan Cara
(
- Vigo U.
)
,
Gopal Ramesh Dahale
(
- Indian Inst. Tech., Bhilai
)
,
Zhongtian Dong
(
- Kansas U.
)
,
Sergei Gleyzer
(
- Alabama U.
)

et al.

- Axioms 13 (2024) 3, 160
•
e-Print:
- 2311.18672
•
DOI:
- 10.3390/axioms13030160

[12]

An Image is Worth 16 × 16 Words: Transformers for Image Recognition at Scale

A. Dosovitskiy
,
L. Beyer
,
A. Kolesnikov
,
D. Weissenborn
,
X. Zhai

et al.

[13]

The Dawn of Quantum Natural Language Processing

•
DOI:
- 10.1109/ICASSP43922.2022.9747675

[14]

Attention is All you Need

I. Guyon
,
U.V. Luxburg
,
S. Bengio
,
H. Wallach
,
R. Fergus

et al.

Quantum self-attention neural networks for text classification

Guangxi Li
(
- Baidu, IQC, Beijing and
- Sydney, U. Technol.
)
,
Xuanqiang Zhao
(
- Baidu, IQC, Beijing
)
,
Xin Wang
(
- Baidu, IQC, Beijing
)

- Sci.China Inf.Sci. 67 (2024) 4, 142501
•
e-Print:
- 2205.05625
•
DOI:
- 10.1007/s11432-023-3879-7

[16]

Quantum Vision Transformers

El Amine Cherrat
(
- IRIF, Paris
)
,
Iordanis Kerenidis
(
- Unlisted, US, CA and
- IRIF, Paris
)
,
Natansh Mathur
(
- IRIF, Paris and
- Unlisted, US, CA
)
,
Jonas Landman
(
- Unlisted, US, CA and
- Edinburgh U.
)
,
Martin Strahm
(
- Unlisted, CH
)

et al.

- Quantum 8 (2024) 1265,
- Quantum 8 (2024) 1265
•
e-Print:
- 2209.08167
•
DOI:
- 10.22331/q-2024-02-22-1265

[17]

Hybrid Quantum Vision Transformers for Event Classification in High Energy Physics

Eyup B. Unlu
(
- Florida U.
)
,
Marçal Comajoan Cara
(
- Vigo U.
)
,
Gopal Ramesh Dahale
(
- Indian Inst. Tech., Bhilai
)
,
Zhongtian Dong
(
- Kansas U.
)
,
Roy T. Forestano
(
- Florida U.
)

et al.

- Axioms 13 (2024) 3, 187,
- Axioms 13 (2024) 187
•
e-Print:
- 2402.00776
•
DOI:
- 10.3390/axioms13030187

[18]

Quantum Graph Transformers

•
DOI:
- 10.1109/ICASSP49357.2023.10096345

[19]

CMS Open Data

[20]

Quark versus Gluon Jet Tagging Using Jet Images with the ATLAS Detector

[21]

New Developments for Jet Substructure Reconstruction in CMS

[22]

Recursive Neural Networks in Quark/Gluon Tagging

Taoli Cheng
(
- Beijing, GUCAS
)

- Comput.Softw.Big Sci. 2 (2018) 1, 3
•
e-Print:
- 1711.02633
•
DOI:
- 10.1007/s41781-018-0007-y

[23]

QCD-Aware Recursive Neural Networks for Jet Physics

- JHEP 01 (2019) 057
•
e-Print:
- 1702.00748
•
DOI:
- 10.1007/JHEP01(2019)057

[24]

End-to-end jet classification of quarks and gluons with the CMS Open Data

M. Andrews
(
- Carnegie Mellon U.
)
,
J. Alison
(
- Carnegie Mellon U.
)
,
S. An
(
- Carnegie Mellon U. and
- CERN
)
,
Patrick Bryant
,
B. Burkle
(
- Brown U.
)

et al.

- Nucl.Instrum.Meth.A 977 (2020) 164304
•
e-Print:
- 1902.08276
•
DOI:
- 10.1016/j.nima.2020.164304

[25]

Deep learning

- Nature 521 (2015) 436-444
•
DOI:
- 10.1038/nature14539

1-25 of 69
1
2
3
25 / page