The DOI matches its Crossref record; 50 of the 50 references it cites were found in a registry or an index.
Searching for new physics with deep autoencoders
Open accessAbstract
We introduce a potentially powerful new method of searching for new physics at the LHC, using autoencoders and unsupervised deep learning. The key idea of the autoencoder is that it learns to map ``normal'' events back to themselves, but fails to reconstruct ``anomalous'' events that it has never encountered before. The reconstruction error can then be used as an anomaly threshold. We demonstrate the effectiveness of this idea using QCD jets as background and boosted top jets and R-parity violating (RPV) gluino jets as signal. We show that a deep autoencoder can significantly improve signal over background when trained on backgrounds only, or even directly on data which contain a small admixture of signal. Finally, we examine the correlation of the autoencoders with jet mass and show how the jet mass distribution can be stable against cuts in reconstruction loss. This may be important for estimating QCD backgrounds from data. As a test case, we show how one could plausibly discover 400 GeV RPV gluinos using an autoencoder combined with a bump hunt in jet mass. This opens up the exciting possibility of training directly on actual data to discover new physics with no prior expectations or theory prejudice.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
Extracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390294 · Cited by 7,436
Sjöstrand, T., Ask, S., Christiansen, J. R., Corke, R., Desai, N., Ilten, P., Mrenna, S., Prestel, S., Rasmussen, C. O., & Skands, P. Z. (2015) · Computer Physics Communications · doi:10.1016/j.cpc.2015.01.024 · Cited by 5,462
DELPHES 3: a modular framework for fast simulation of a generic collider experiment
The DELPHES 3 collaboration, de Favereau, J., Delaere, C., Demin, P., Giammanco, A., Lemaître, V., Mertens, A., & Selvaggi, M. (2014) · Journal of High Energy Physics · doi:10.1007/jhep02(2014)057 · Cited by 2,966
Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
Schlegl, T., Seeböck, P., Waldstein, S. M., Schmidt-Erfurth, U., & Langs, G. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-59050-9_12 · Cited by 2,627
Generative Adversarial Networks
(2022) · The Science of Deep Learning · doi:10.1017/9781108891530.013 · Cited by 2,402
Neural networks and principal component analysis: Learning from examples without local minima
Baldi, P., & Hornik, K. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90014-2 · Cited by 1,383
Deep learning and its application to LHC physics
Guest, D., Cranmer, K., & Whiteson, D. (2018) · Annual Review of Nuclear and Particle Science · doi:10.1146/annurev-nucl-101917-021019 · Cited by 417 · cited 1×
“Applications of deep learning in high energy physics do not stop at classification tasks: pile-up removal [32], generative models [33] and many others (for a review and more references, we refer to [34]) have all been studied.”
Backgroundde Oliveira, L., Paganini, M., & Nachman, B. (2017) · Computing and Software for Big Science · doi:10.1007/s41781-017-0004-6 · Cited by 293
Deep learning in color: towards automated quark/gluon jet discrimination
Komiske, P. T., Metodiev, E. M., & Schwartz, M. D. (2017) · Journal of High Energy Physics · doi:10.1007/jhep01(2017)110 · Cited by 291
Jet-images — deep learning edition
de Oliveira, L. (2022) · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · doi:10.1007/jhep07%282016%29069 · Cited by 291
Classification without labels: learning from mixed samples in high energy physics
Metodiev, E. M., Nachman, B., & Thaler, J. (2017) · Journal of High Energy Physics · doi:10.1007/jhep10(2017)174 · Cited by 287
Jet-images — deep learning edition
de Oliveira, L., Kagan, M., Mackey, L., Nachman, B., & Schwartzman, A. (2016) · Journal of High Energy Physics · doi:10.1007/jhep07(2016)069 · Cited by 282
Heimel, T., Kasieczka, G., Plehn, T., & Thompson, J. (2019) · SciPost Physics · doi:10.21468/scipostphys.6.3.030 · Cited by 279
Deep-learning top taggers or the end of QCD?
Kasieczka, G., Plehn, T., Russell, M., & Schell, T. (2017) · Journal of High Energy Physics · doi:10.1007/jhep05(2017)006 · Cited by 276
Jet substructure classification in high-energy physics with deep neural networks
Baldi, P., Bauer, K., Eng, C., Sadowski, P., & Whiteson, D. (2016) · Physical Review D · doi:10.1103/physrevd.93.094034 · Cited by 248
Anomaly Detection for Resonant New Physics with Machine Learning
Collins, J., Howe, K., & Nachman, B. (2018) · Physical Review Letters · doi:10.1103/physrevlett.121.241803 · Cited by 248
JUNIPR: a framework for unsupervised machine learning in particle physics
Andreassen, A., Feige, I., Frye, C., & Schwartz, M. D. (2019) · The European Physical Journal C · doi:10.1140/epjc/s10052-019-6607-9 · Cited by 222
Playing tag with ANN: boosted top identification with pattern recognition
Almeida, L. G., Backović, M., Cliche, M., Lee, S. J., & Perelstein, M. (2015) · Journal of High Energy Physics · doi:10.1007/jhep07(2015)086 · Cited by 211
Learning new physics from a machine
D’Agnolo, R. T., & Wulzer, A. (2019) · Physical Review D · doi:10.1103/physrevd.99.015014 · Cited by 203
Deep-learned Top Tagging with a Lorentz Layer
Butter, A., Kasieczka, G., Plehn, T., & Russell, M. (2018) · SciPost Physics · doi:10.21468/scipostphys.5.3.028 · Cited by 193
Pulling out all the tops with computer vision and deep learning
Macaluso, S., & Shih, D. (2018) · Journal of High Energy Physics · doi:10.1007/jhep10(2018)121 · Cited by 193
Self-citationDeep learning in color: towards automated quark/gluon jet discrimination
Schwartz, M. D. (2022) · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · doi:10.1007/jhep01%282017%29110 · Cited by 185
QCD-Aware Recursive Neural Networks for Jet Physics
Louppe, G., Cho, K., Becot, C., & Cranmer, K. S. (2017) · Open Repository and Bibliography (University of Liège) · Cited by 181
Jet-images: computer vision inspired techniques for jet tagging
Cogan, J., Kagan, M., Strauss, E., & Schwarztman, A. (2015) · Journal of High Energy Physics · doi:10.1007/jhep02(2015)118 · Cited by 177
Novelty detection meets collider physics
Hajer, J., Li, Y.-Y., Liu, T., & Wang, H. (2020) · Physical review. D/Physical review. D. · doi:10.1103/physrevd.101.076015 · Cited by 166
Pulling out all the tops with computer vision and deep learning
Macaluso, S. (2022) · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · doi:10.1007/jhep10%282018%29121 · Cited by 158
Chang, S., Timothy Cohen, A., & Ostdiek, B. (2018) · Physical review. D/Physical review. D. · doi:10.1103/physrevd.97.056009 · Cited by 156
Guiding new physics searches with unsupervised learning
Andrea De Simone, A., & Jacques, T. (2019) · The European Physical Journal C · doi:10.1140/epjc/s10052-019-6787-3 · Cited by 140
Jet Constituents for Deep Neural Network Based Top Quark TaggingPreprint
Pearkes, J., Fedorko, W. T., LISTER, A., & Gay, C. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.02124 · Cited by 138
Deep-learning top taggers or the end of QCD
Kasieczka, G., Plehn, T., Russell, M., & Schell, T. (2017) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-b-000191242 · Cited by 136
Parton shower uncertainties in jet substructure analyses with deep neural networks
Barnard, J., Dawe, E., Dolan, M. J., & Rajcic, N. (2017) · Physical review. D/Physical review. D. · doi:10.1103/physrevd.95.014018 · Cited by 135
Weakly supervised classification in high energy physics
Dery, L. M., Nachman, B. P., Rubbo, F., & Schwartzman, A. G. (2017) · Journal of High Energy Physics · doi:10.1007/jhep05(2017)145 · Cited by 124
QCD-aware recursive neural networks for jet physics
Louppe, G., Cho, K., Becot, C., & Cranmer, K. (2019) · Journal of High Energy Physics · doi:10.1007/jhep01(2019)057 · Cited by 123
Weakly supervised classification in high energy physics
Dery, L. M. (2022) · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · doi:10.1007/jhep05%282017%29145 · Cited by 118
Pileup Mitigation with Machine Learning (PUMML)
Komiske, P., Metodiev, E. M., Nachman, B. P., et al. (2017) · Journal of High Energy Physics · doi:10.1007/jhep12(2017)051 · Cited by 114
Jet Topics: Disentangling Quarks and Gluons at Colliders
Metodiev, E. M., & Thaler, J. (2018) · Physical Review Letters · doi:10.1103/physrevlett.120.241602 · Cited by 111
(Machine) learning to do more with less
Timothy Cohen, A. (2024) · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · doi:10.1007/jhep02%282018%29034 · Cited by 99
(Machine) learning to do more with less
Timothy Cohen, A., Freytsis, M., & Ostdiek, B. (2018) · Journal of High Energy Physics · doi:10.1007/jhep02(2018)034 · Cited by 96
Deep-learned Top Tagging with a Lorentz Layer
Butter, A., Kasieczka, G., Plehn, T., & Russell, M. (2018) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-b-000415419 · Cited by 90
Long Short-Term Memory (LSTM) networks with jet constituents for boosted top tagging at the LHCPreprint
Egan, S., Fedorko, W., Lister, A., Pearkes, J., & Gay, C. (2017) · arXiv.org · doi:10.48550/arxiv.1711.09059 · Cited by 89
Probing stop pair production at the LHC with graph neural networks
Abdughani, M., Ren, J., Wu, L., & Yang, J. M. (2019) · Journal of High Energy Physics · doi:10.1007/jhep08(2019)055 · Cited by 85
Recursive Neural Networks in Quark/Gluon Tagging
Cheng, T. (2018) · Computing and Software for Big Science · doi:10.1007/s41781-018-0007-y · Cited by 84
Deep Neural Networks for Physics Analysis on low-level whole-detector data at the LHC
Bhimji, W., Farrell, S., Kurth, T., Paganini, M., Prabhat, & Racah, E. (2018) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1085/4/042034 · Cited by 57
Generative Adversarial Networks
Arora, J. K., Tushir, M., Kherwa, P., & Rathee, S. (2023) · Wiley eBooks · doi:10.1002/9781119879862.ch10 · Cited by 40
Topology Classification with Deep Learning to Improve Real-Time Event Selection at the LHC
Nguyen, T. Q., Weitekamp, D., Anderson, D., Castello, R., Cerri, O., Pierini, M., Spiropulu, M., & Vlimant, J.-R. (2019) · Computing and Software for Big Science · doi:10.1007/s41781-019-0028-1 · Cited by 34
Deep learning for R -parity violating supersymmetry searches at the LHC
Guo, J., Li, J., Li, T., Xu, F. Z., & Zhang, W. (2018) · Physical review. D/Physical review. D. · doi:10.1103/physrevd.98.076017 · Cited by 29
Pol, A. A., Cerminara, G., Germain‐Renaud, C., Maurizio Pierini, B., & Seth, A. (2019) · Computing and Software for Big Science · doi:10.1007/s41781-018-0020-1 · Cited by 29
Spectral analysis of jet substructure with neural networks: boosted Higgs case
Lim, S. H., & Nojiri, M. M. (2018) · Institutional Repositories DataBase (IRDB) · Cited by 28
Spectral analysis of jet substructure with neural networks: boosted Higgs case
Lim, S. H., & Nojiri, M. M. (2018) · Journal of High Energy Physics · doi:10.1007/jhep10(2018)181 · Cited by 27
Cited by
Anomaly detection with density estimation
Nachman, B., & Shih, D. (2020) · Physical Review D · doi:10.1103/physrevd.101.075042 · Cited by 291
Self-citation
Metadata
- Authors
- Farina, M., Nakai, Y., & Shih, D.
- Venue
- Physical Review D
- Publisher
- American Physical Society (APS)
- Published
- 2020-04-13
- Volume
- 101
- Issue
- 7
- ISSN
- 2470-0010 (ISSN-L)
- 2470-0029
- OpenAlex
- W2889504592
- Cited by
- 266
- References
- 50
- FWCI
- 20.73
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.