Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Challenges and opportunities in quantum machine learning for high-energy physics

Nature Reviews Physics volume 4, pages 143–144 (2022)Cite this article

Subjects

Quantum machine learning may provide powerful tools for data analysis in high-energy physics. Sau Lan Wu and Shinjae Yoo describe how the potential of these tools is starting to be tested and what has been understood thus far.

As the Large Hadron Collider (LHC) experiments enter the post-Higgs discovery era, one of the major objectives of the experimental programmes at the LHC is the discovery of new physics. Doing so requires the identification of rare signals in immense backgrounds — the discovery of the Higgs boson ten years ago required sifting through data from 1015 proton–proton collisions per experiment, and the ambitious high-luminosity LHC (HL-LHC) programme will produce more than 300 times as much data. Machine learning is well-suited for such a task, and was already in use in the Higgs analysis, but analysing the ever-larger volumes of data will require increasing computing resources in the next two decades. In the face of such big high-dimensional data sets, quantum machine learning (QML) holds promise1,2. Because it efficiently operates in the high-dimensional quantum state space, QML offers potential computational speed-ups and better classification performance than classical machine learning. With the progress of quantum technologies, QML could become a powerful tool for data analysis in high-energy physics (HEP), because it could potentially accelerate certain types of classically expensive operations, including eigensolvers. In addition, qubit representations for both data and states (also known as embedding or code space) offer better compression. Now, researchers in HEP are starting to test whether, and in what circumstances, QML lives up to this promise.

This is a preview of subscription content, access via your institution

Access options

Rent or buy this article

Get just this article for as long as you need it

$39.95

Learn more

Prices may be subject to local taxes which are calculated during checkout

References

  1. Havlek, V. et al. Supervised learning with quantum-enhanced feature spaces. Nature 567, 209–212 (2019).

    Article  ADS  Google Scholar 

  2. Schuld, M. & Killoran, N. Quantum machine learning in feature Hilbert spaces. Phys. Rev. Lett. 122, 040504 (2019).

    Article  ADS  Google Scholar 

  3. Wu, S. L. et al. Application of quantum machine learning using the quantum variational classifier method to high energy physics analysis at the LHC on IBM quantum computer simulator and hardware with 10 qubits. J. Phys. G: Nucl. Part. Phys 48, 125003 (2021).

    Article  ADS  Google Scholar 

  4. Wu, S. L. et al. Application of quantum machine learning using the quantum kernel algorithm on high energy physics analysis at the LHC. Phys. Rev. Res. 3, 033221 (2021).

    Article  Google Scholar 

  5. The DELPHES 3 collaboration. et al. DELPHES 3: a modular framework for fast simulation of a generic collider experiment. J. High Energy Phys. 2014, 57 (2014).

    Google Scholar 

  6. Eddins, A. et al. Doubling the size of quantum simulators by entanglement forging. PRX Quantum 3, 010309 (2022).

  7. Zhukov, A. A. & Pogosov, W. V. Quantum error reduction with deep neural network applied at the post-processing stage. Preprint at https://arxiv.org/abs/2105.07793 (2021).

  8. Maciejewski, F. B., Zimborás, Z. & Oszmanie, M. Mitigation of readout noise in near-term quantum devices by classical post-processing based on detector tomography. Quantum 4, 257 (2020).

    Article  Google Scholar 

  9. Mott, A. et al. Solving a Higgs optimization problem with quantum annealing for machine learning. Nature 550, 375–379 (2017).

    Article  ADS  Google Scholar 

Download references

Acknowledgements

This work is supported in part by the United States Department of Energy, Office of Science, High Energy Physics QuantISED Program, under Award Number DE-SC-0020416 and DE-SC-0012704 and by the Vilas foundation at the University of Wisconsin.

Author information

Authors and Affiliations

  1. Physics Department, University of Wisconsin-Madison, Madison, WI, USA

    Sau Lan Wu

  2. Computational Science Initiative, Brookhaven National Laboratory, Upton, NY, USA

    Shinjae Yoo

Authors
  1. Sau Lan Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shinjae Yoo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sau Lan Wu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Related links

Google quantum computing journey: https://quantumai.google/learn/map

IBM’s roadmap for scaling quantum technology: https://research.ibm.com/blog/ibm-quantum-roadmap

IonQ’s Roadmap up to 2025: https://ionq.com/posts/december-09-2020-scaling-quantum-computer-roadmap

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wu, S.L., Yoo, S. Challenges and opportunities in quantum machine learning for high-energy physics. Nat Rev Phys 4, 143–144 (2022). https://doi.org/10.1038/s42254-022-00425-7

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42254-022-00425-7

This article is cited by

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing