Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
8 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Quantum Vision Transformers for Quark-Gluon Classification (2405.10284v1)

Published 16 May 2024 in quant-ph, cs.LG, and hep-ph

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (69)
  1. CERN. The HL-LHC Project. 2022. Available online: https://hilumilhc.web.cern.ch/content/hl-lhc-project (accessed on 24 September 2023).
  2. Challenges in Monte Carlo Event Generator Software for High-Luminosity LHC. Comput. Softw. Big Sci. 2021, 5, 12. [CrossRef]
  3. A Survey of Quantum Learning Theory. arXiv 2017, arXiv:1701.06806. [CrossRef]
  4. Quantum machine learning. Nature 2017, 549, 195–202. [CrossRef] [PubMed]
  5. Quantum Machine Learning in Feature Hilbert Spaces. Phys. Rev. Lett. 2019, 122, 040504. [CrossRef] [PubMed]
  6. Quantum computing models for artificial neural networks. Europhys. Lett. 2021, 134, 10002. [CrossRef]
  7. A rigorous and robust quantum speed-up in supervised machine learning. Nat. Phys. 2021, 17, 1013–1017. [CrossRef]
  8. Quantum advantage in learning from experiments. Science 2022, 376, 1182–1186. [CrossRef]
  9. Generalization in quantum machine learning from few training data. Nat. Commun. 2022, 13, 4919. [CrossRef] [PubMed]
  10. Z2×Z2subscript𝑍2subscript𝑍2Z_{2}\times Z_{2}italic_Z start_POSTSUBSCRIPT 2 end_POSTSUBSCRIPT × italic_Z start_POSTSUBSCRIPT 2 end_POSTSUBSCRIPT Equivariant Quantum Neural Networks: Benchmarking against Classical Neural Networks. Axioms 2024, 13, 188 . [CrossRef]
  11. A Comparison between Invariant and Equivariant Classical and Quantum Graph Neural Networks. Axioms 2024, 13, 160. [CrossRef]
  12. An Image is Worth 16 ×\times× 16 Words: Transformers for Image Recognition at Scale. In Proceedings of the International Conference on Learning Representations, Online, 3–7 May 2021.
  13. The Dawn of Quantum Natural Language Processing. In Proceedings of the ICASSP 2022—2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, 23–27 May 2022; pp. 8612–8616. [CrossRef]
  14. Attention is All you Need. In Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA, 4–9 December 2017; Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R., Eds.; Curran Associates, Inc.: New York, NY, USA, 2017; Volume 30.
  15. Quantum Self-Attention Neural Networks for Text Classification. arXiv 2022, arXiv:2205.05625. [CrossRef]
  16. Quantum Vision Transformers. Quantum 2024, 8, 1265. [CrossRef]
  17. Hybrid Quantum Vision Transformers for Event Classification in High Energy Physics. Axioms 2024, 13, 187. [CrossRef]
  18. Quantum Graph Transformers. In Proceedings of the ICASSP 2023—2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 4–10 June 2023; pp. 1–5. [CrossRef]
  19. CERN. CMS Open Data. 2023. Available online: http://opendata.cern.ch/docs/about-cms (accessed on 24 September 2023).
  20. The ATLAS Collaboration. Quark versus Gluon Jet Tagging Using Jet Images with the ATLAS Detector; Technical Report; CERN: Geneva, Switzerland, 2017. Available online: https://cds.cern.ch/record/2275641 (accessed on 12 May 2024).
  21. The CMS Collaboration. New Developments for Jet Substructure Reconstruction in CMS. 2017. Available online: https://cds.cern.ch/record/2275226 (accessed on 8 May 2024 ).
  22. Cheng, T. Recursive Neural Networks in Quark/Gluon Tagging. Comput. Softw. Big Sci. 2018, 2, 3. [CrossRef]
  23. QCD-aware recursive neural networks for jet physics. J. High Energy Phys. 2019, 2019, 57. [CrossRef]
  24. End-to-end jet classification of quarks and gluons with the CMS Open Data. Nucl. Instrum. Methods Phys. Res. Sect. A Accel. Spectrometers Detect. Assoc. Equip. 2020, 977, 164304. [CrossRef]
  25. Deep learning. Nature 2015, 521, 436–444. [CrossRef]
  26. Deep Learning, 1st ed.; Springer: Cham, Switzerland, 2023.
  27. Schmidhuber, J. Annotated History of Modern AI and Deep Learning. arXiv 2022, arXiv:2212.11279.
  28. Fukushima, K. Visual Feature Extraction by a Multilayered Network of Analog Threshold Elements. IEEE Trans. Syst. Sci. Cybern. 1969, 5, 322–333. [CrossRef]
  29. Deep sparse rectifier neural networks. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, Fort Lauderdale, FL, USA, 11–13 April 2011; pp. 315–323.
  30. Gaussian Error Linear Units (GELUs). arXiv 2016, arXiv:1606.08415.
  31. Layer normalization. arXiv 2016, arXiv:1607.06450.
  32. Deep Residual Learning for Image Recognition. arXiv 2015, arXiv:1512.03385.
  33. Better plain ViT baselines for ImageNet-1k. arXiv 2022, arXiv:2205.01580. [CrossRef]
  34. Quantum Support Vector Machine for Big Data Classification. Phys. Rev. Lett. 2014, 113, 130503. [CrossRef]
  35. Quantum Algorithms for Nearest-Neighbor Methods for Supervised and Unsupervised Learning. Quantum Inf. Comput. 2015, 15, 316–356.
  36. Nearest centroid classification on a trapped ion quantum computer. npj Quantum Inf. 2021, 7, 122. [CrossRef]
  37. Kinematic variables and feature engineering for particle phenomenology. Rev. Mod. Phys. 2023, 95, 045004. [CrossRef]
  38. QCD and Collider Physics; Cambridge University Press: Cambdrige, UK, 2011; Volume 8. [CrossRef]
  39. Salam, G.P. Towards Jetography. Eur. Phys. J. C 2010, 67, 637–686. [CrossRef]
  40. Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning. Phys. Rept. 2020, 841, 1–63. [CrossRef]
  41. Jet Substructure at the Large Hadron Collider: Experimental Review. Rev. Mod. Phys. 2019, 91, 045003. [CrossRef]
  42. Looking Inside Jets: An Introduction to Jet Substructure and Boosted-Object Phenomenology; Springer: Berlin/Heidelberg, Germany, 2019; Volume 958. [CrossRef]
  43. A Living Review of Machine Learning for Particle Physics. arXiv 2021, arXiv:2102.02770.
  44. Deep Learning and its Application to LHC Physics. Ann. Rev. Nucl. Part. Sci. 2018, 68, 161–181. [CrossRef]
  45. Machine Learning in High Energy Physics Community White Paper. J. Phys. Conf. Ser. 2018, 1085, 022008. [CrossRef]
  46. Machine learning at the energy and intensity frontiers of particle physics. Nature 2018, 560, 41–48. [CrossRef] [PubMed]
  47. Machine learning and the physical sciences. Rev. Mod. Phys. 2019, 91, 045002. [CrossRef]
  48. Bourilkov, D. Machine and Deep Learning Applications in Particle Physics. Int. J. Mod. Phys. A 2020, 34, 1930019. [CrossRef]
  49. Schwartz, M.D. Modern Machine Learning and Particle Physics. arXiv 2021, arXiv:2103.12226. [CrossRef]
  50. Machine Learning in the Search for New Fundamental Physics. arXiv 2021, arXiv:2112.03769.
  51. Colloquium: Machine learning in nuclear physics. Rev. Mod. Phys. 2022, 94, 031003. [CrossRef]
  52. Snowmass 2021 Computational Frontier CompF03 Topical Group Report: Machine Learning. arXiv 2022, arXiv:2209.07559.
  53. The CMS Experiment at the CERN LHC. JINST 2008, 3, S08004. [CrossRef]
  54. CMS Collaboration. Description and performance of track and primary-vertex reconstruction with the CMS tracker. JINST 2014, 9, P10009. [CrossRef]
  55. CMS Collaboration. Energy Calibration and Resolution of the CMS Electromagnetic Calorimeter in p⁢p𝑝𝑝ppitalic_p italic_p Collisions at s=7𝑠7\sqrt{s}=7square-root start_ARG italic_s end_ARG = 7 TeV. JINST 2013, 8, P09009. [CrossRef]
  56. Design, performance, and calibration of CMS hadron-barrel calorimeter wedges. Eur. Phys. J. C 2008, 55, 159–171. [CrossRef]
  57. Design, performance, and calibration of the CMS Hadron-outer calorimeter. Eur. Phys. J. C 2008, 57, 653–663. [CrossRef]
  58. CMS Coordinate System. Available online: https://tikz.net/axis3d_cms/ (accessed on 6 March 2024).
  59. Quantum utility—Definition and assessment of a practical quantum advantage. In Proceedings of the 2023 IEEE International Conference on Quantum Software, Chicago, IL, USA, 2–8 July 2023; pp. 162–174. [CrossRef]
  60. Decoupled Weight Decay Regularization. arXiv 2019, arXiv:1711.05101. [CrossRef]
  61. SGDR: Stochastic Gradient Descent with Warm Restarts. arXiv 2017, arXiv:1608.03983.
  62. JAX: Composable Transformations of Python+NumPy Programs. 2023. Available online: http://github.com/google/jax (accessed on 24 September 2023).
  63. Flax: A Neural Network Library and Ecosystem for JAX. 2023. Available online: http://github.com/google/flax (accessed on 24 September 2023).
  64. TensorCircuit: A Quantum Software Framework for the NISQ Era. Quantum 2023, 7, 912. [CrossRef]
  65. How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers. arXiv 2022, arXiv:2106.10270. [CrossRef]
  66. RandAugment: Practical Automated Data Augmentation with a Reduced Search Space. In Proceedings of the Advances in Neural Information Processing Systems, Online, 6–12 December 2020; Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H., Eds.; Curran Associates, Inc.: Red Hook, NY, USA, 2020; Volume 33, pp. 18613–18624.
  67. mixup: Beyond Empirical Risk Minimization. In Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada, 30 April–3 May 2018.
  68. Data re-uploading for a universal quantum classifier. Quantum 2020, 4, 226. [CrossRef]
  69. Is the machine smarter than the theorist: Deriving formulas for particle kinematics with symbolic regression. Phys. Rev. D 2023, 107, 055018. [CrossRef]
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now