Publications

This page includes links to my publication history, some aggregate bibliometrics, and some selected publications organized by research theme.

All publications
1,200 Publications 349,000 Citations 241 h-index
Publications with <20 authors
119 Publications 14,000 Citations 41 h-index

Selected Publications

Simulation-based Inference Methodology

Developing statistical methods for inference when likelihoods are intractable but simulators are available.

  1. ★ Kyle Cranmer, Johann Brehmer, and Gilles Louppe. The frontier of simulation-based inference. Proc. Nat. Acad. Sci., 117(48):30055–30062, 2020. arXiv:1911.01429, doi:10.1073/pnas.1912789117. [1037 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  2. Johann Brehmer, Gilles Louppe, Juan Pavez, and Kyle Cranmer. Mining gold from implicit models to improve likelihood-free inference. Proc. Nat. Acad. Sci., 117(10):5242–5249, 2020. arXiv:1805.12244, doi:10.1073/pnas.1915980117. [157 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  3. Johann Brehmer, Kyle Cranmer, Gilles Louppe, and Juan Pavez. Constraining Effective Field Theories with Machine Learning. Phys. Rev. Lett., 121(11):111801, 2018. arXiv:1805.00013, doi:10.1103/PhysRevLett.121.111801. [164 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  4. Johann Brehmer, Kyle Cranmer, Gilles Louppe, and Juan Pavez. A Guide to Constraining Effective Field Theories with Machine Learning. Phys. Rev. D, 98(5):052004, 2018. arXiv:1805.00020, doi:10.1103/PhysRevD.98.052004. [145 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  5. Markus Stoye, Johann Brehmer, Gilles Louppe, Juan Pavez, and Kyle Cranmer. Likelihood-free inference with an improved cross-entropy estimator. NeurIPS ML4PS Workshop, 2018. arXiv:1808.00973. [arXiv] [BibTeX] [show altmetrics]
  6. Gilles Louppe, Joeri Hermans, and Kyle Cranmer. Adversarial Variational Optimization of Non-Differentiable Simulators. PMLR, 89:1438–1447, 2019. arXiv:1707.07113. [arXiv] [BibTeX] [show altmetrics]
  7. Kyle Cranmer and Gilles Louppe. Unifying generative models and exact likelihood-free inference with conditional bijections. 2015. doi:10.5281/zenodo.198541. [12 citations] [DOI] [BibTeX] [show altmetrics]

Generative Models: Normalizing Flows on Manifolds

Neural density estimation on non-Euclidean spaces.

  1. Johann Brehmer and Kyle Cranmer. Flows for simultaneous manifold learning and density estimation. Advances in Neural Information Processing Systems, 2020. arXiv:2003.13913. [175 citations] [arXiv] [BibTeX] [show altmetrics]
  2. Danilo Jimenez Rezende, George Papamakarios, Sebastien Racaniere, Michael S. Albergo, Gurtej Kanwar, Phiala E. Shanahan, and Kyle Cranmer. Normalizing Flows on Tori and Spheres. International Conference on Machine Learning (ICML), 2020. arXiv:2002.02428. [arXiv] [BibTeX] [show altmetrics]

AI-Enhanced Sampling for Lattice Field Theory

Machine learning approaches to sampling in lattice QCD and other field theories.

  1. ★ Kyle Cranmer, Gurtej Kanwar, Sebastien Racaniere, Danilo J. Rezende, and Phiala E. Shanahan. Advances in machine-learning-based sampling motivated by lattice quantum chromodynamics. Nature Rev. Phys., 5(9):526–535, 2023. arXiv:2309.01156, doi:10.1038/s42254-023-00616-w. [25 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  2. Michael S. Albergo, Denis Boyda, Kyle Cranmer, Daniel C. Hackett, Gurtej Kanwar, and others. Flow-based sampling in the lattice Schwinger model at criticality. Phys. Rev. D, 106(1):014514, 2022. arXiv:2202.11712, doi:10.1103/PhysRevD.106.014514. [34 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  3. Denis Boyda, Gurtej Kanwar, Sebastien Racaniere, Danilo Jimenez Rezende, Michael S. Albergo, Kyle Cranmer, and others. Sampling using SU(N) gauge equivariant flows. Phys. Rev. D, 103(7):074504, 2021. arXiv:2008.05456, doi:10.1103/PhysRevD.103.074504. [104 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  4. Daniel C. Hackett, Chung-Chun Hsieh, Michael S. Albergo, Denis Boyda, Jiunn-Wei Chen, and others. Flow-based sampling for multimodal distributions in lattice field theory. 2021. arXiv:2107.00734. [46 citations] [arXiv] [BibTeX] [show altmetrics]
  5. Michael S. Albergo, Gurtej Kanwar, Sebastien Racaniere, Danilo J. Rezende, Julian M. Urban, and others. Flow-based sampling for fermionic lattice field theories. Phys. Rev. D, 104(11):114507, 2021. arXiv:2106.05934, doi:10.1103/PhysRevD.104.114507. [arXiv] [DOI] [BibTeX] [show altmetrics]
  6. Michael S. Albergo, Denis Boyda, Daniel C. Hackett, Gurtej Kanwar, Kyle Cranmer, and others. Introduction to Normalizing Flows for Lattice Field Theory. 2021. arXiv:2101.08176. [63 citations] [arXiv] [BibTeX] [show altmetrics]
  7. Gurtej Kanwar, Michael S. Albergo, Denis Boyda, Kyle Cranmer, Daniel C. Hackett, and others. Equivariant flow-based sampling for lattice gauge theory. Phys. Rev. Lett., 125(12):121601, 2020. arXiv:2003.06413, doi:10.1103/PhysRevLett.125.121601. [185 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]

AI for Astrophysics

Machine learning methods for astrophysical inference and dark matter searches.

  1. Siddharth Mishra-Sharma and Kyle Cranmer. Neural simulation-based inference approach for characterizing the Galactic Center gamma-ray excess. Phys. Rev. D, 105(6):063017, 2022. arXiv:2110.06931, doi:10.1103/PhysRevD.105.063017. [37 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  2. Siddharth Mishra-Sharma and Kyle Cranmer. Semi-parametric gamma-ray modeling with Gaussian processes and variational inference. NeurIPS ML4PS Workshop, 2020. arXiv:2010.10450. [arXiv] [BibTeX] [show altmetrics]
  3. Johann Brehmer, Siddharth Mishra-Sharma, Joeri Hermans, Gilles Louppe, and Kyle Cranmer. Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning. Astrophys. J., 886(1):49, 2019. arXiv:1909.02005, doi:10.3847/1538-4357/ab4c41. [72 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]

Sets, Graphs, and Trees: AI for or Inspired by Jet Physics

Novel neural network architectures motivated by the hierarchical structure of particle jets.

  1. Sebastian Macaluso and Kyle Cranmer. The Quantum Trellis: A classical algorithm for sampling the parton shower with interference effects. NeurIPS ML4PS Workshop, 2021. arXiv:2112.12795. [arXiv] [BibTeX] [show altmetrics]
  2. Kyle Cranmer, Matthew Drnevich, Sebastian Macaluso, and Duccio Pappadopulo. Reframing Jet Physics with New Computational Methods. EPJ Web Conf., 251:03059, 2021. arXiv:2105.10512, doi:10.1051/epjconf/202125103059. [15 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  3. Craig S. Greenberg, Sebastian Macaluso, Nicholas Monath, Avinava Dubey, Patrick Flaherty, and others. Exact and Approximate Hierarchical Clustering Using A*. UAI, 161:2061–2071, 2021. arXiv:2104.07061. [arXiv] [BibTeX] [show altmetrics]
  4. Johann Brehmer, Sebastian Macaluso, Duccio Pappadopulo, and Kyle Cranmer. Hierarchical clustering in particle physics through reinforcement learning. NeurIPS ML4PS Workshop, 2020. arXiv:2011.08191. [6 citations] [arXiv] [BibTeX] [show altmetrics]
  5. Craig S. Greenberg, Sebastian Macaluso, Nicholas Monath, Ji-Ah Lee, Patrick Flaherty, and others. Data Structures and Algorithms for Exact Inference in Hierarchical Clustering. AISTATS, 2021. arXiv:2002.11661. [3 citations] [arXiv] [BibTeX] [show altmetrics]
  6. Jonathan Shlomi, Sanmay Ganguly, Eilam Gross, Kyle Cranmer, Yaron Lipman, and others. Secondary vertex finding in jets with neural networks. Eur. Phys. J. C, 81(6):540, 2021. arXiv:2008.02831, doi:10.1140/epjc/s10052-021-09342-y. [18 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  7. Hadar Serviansky, Nimrod Segol, Jonathan Shlomi, Kyle Cranmer, Eilam Gross, and others. Set2Graph: Learning Graphs From Sets. Advances in Neural Information Processing Systems, 2020. arXiv:2002.08772. [36 citations] [arXiv] [BibTeX] [show altmetrics]
  8. Gilles Louppe, Kyunghyun Cho, Cyril Becot, and Kyle Cranmer. QCD-Aware Recursive Neural Networks for Jet Physics. JHEP, 01:057, 2019. arXiv:1702.00748, doi:10.1007/JHEP01(2019)057. [113 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  9. Isaac Henrion, Kyle Cranmer, Joan Bruna, Kyunghyun Cho, Johann Brehmer, Gilles Louppe, and Gaspar Rochette. Neural Message Passing for Jet Physics. In Deep Learning for Physical Sciences Workshop, NeurIPS. 2017. [BibTeX]

Universal Probabilistic Programming

Probabilistic programming approaches for scientific simulators.

  1. Atilim Gunes Baydin, Lei Shao, Wahid Bhimji, Lukas Heinrich, Lawrence Meadows, and others. Etalumis: bringing probabilistic programming to scientific simulators at scale. SC19, 2019. arXiv:1907.03382, doi:10.1145/3295500.3356180. [27 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  2. Atilim Gunes Baydin, Lukas Heinrich, Wahid Bhimji, Lei Shao, Saeid Naderiparizi, and others. Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model. Advances in Neural Information Processing Systems, 2020. arXiv:1807.07706. [32 citations] [arXiv] [BibTeX] [show altmetrics]
  3. Mario Lezcano Casado, Atilim Gunes Baydin, David Martinez Rubio, Tuan Anh Le, Frank Wood, Lukas Heinrich, Gilles Louppe, Kyle Cranmer, Wahid Bhimji, Karen Ng, and Prabhat. Improvements to Inference Compilation for Probabilistic Programming in Large-Scale Scientific Simulators. In Deep Learning for Physical Sciences Workshop, NeurIPS. 2017. [BibTeX]

Graph and Neuro-Symbolic Approaches for Dynamical Systems

Combining neural networks with physical structure for modeling dynamical systems.

  1. Miles Cranmer, Alvaro Sanchez-Gonzalez, Peter Battaglia, Rui Xu, Kyle Cranmer, and others. Discovering Symbolic Models from Deep Learning with Inductive Biases. Advances in Neural Information Processing Systems, 2020. arXiv:2006.11287. [571 citations] [arXiv] [BibTeX] [show altmetrics]
  2. Alvaro Sanchez-Gonzalez, Victor Bapst, Kyle Cranmer, and Peter Battaglia. Hamiltonian Graph Networks with ODE Integrators. NeurIPS ML4PS Workshop, 2019. arXiv:1909.12790. [187 citations] [arXiv] [BibTeX] [show altmetrics]

Miscellaneous AI for Science

Other applications of machine learning to scientific problems.

  1. Tianji Cai, Garrett W. Merz, Francois Charton, Niklas Nolte, Matthias Wilhelm, Kyle Cranmer, and Lance J. Dixon. Transforming the bootstrap: using transformers to compute scattering amplitudes. Mach. Learn. Sci. Tech., 5(3):035073, 2024. arXiv:2405.06107, doi:10.1088/2632-2153/ad743e. [8 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  2. Abhijith Gandrakota, Lily H. Zhang, Aahlad Puli, Kyle Cranmer, Jennifer Ngadiuba, and others. Robust anomaly detection for particle physics using multi-background representation learning. Mach. Learn. Sci. Tech., 5(3):035082, 2024. arXiv:2401.08777, doi:10.1088/2632-2153/ad780c. [3 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  3. Kyle Cranmer, Siavash Golkar, and Duccio Pappadopulo. Inferring the quantum density matrix with machine learning. NeurIPS ML4PS Workshop, 2019. arXiv:1904.05903. [18 citations] [arXiv] [BibTeX] [show altmetrics]
  4. Siavash Golkar and Kyle Cranmer. Backdrop: Stochastic Backpropagation. NeurIPS ML4PS Workshop, 2018. arXiv:1806.01337. [2 citations] [arXiv] [BibTeX] [show altmetrics]
  5. Meghan Frate, Kyle Cranmer, Saarik Kalia, Alexander Vandenberg-Rodes, and Daniel Whiteson. Modeling Smooth Backgrounds and Generic Localized Signals with Gaussian Processes. 2017. arXiv:1709.05681. [52 citations] [arXiv] [BibTeX] [show altmetrics]
  6. Gilles Louppe, Michael Kagan, and Kyle Cranmer. Learning to Pivot with Adversarial Networks. Advances in Neural Information Processing Systems, 30:981–990, 2017. arXiv:1611.01046. [235 citations] [arXiv] [BibTeX] [show altmetrics]
  7. Pierre Baldi, Kyle Cranmer, Taylor Faucett, Peter Sadowski, and Daniel Whiteson. Parameterized neural networks for high-energy physics. Eur. Phys. J. C, 76(5):235, 2016. arXiv:1601.07913, doi:10.1140/epjc/s10052-016-4099-4. [257 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]

AI/ML Reviews

Review articles on machine learning for science.

  1. Particle Data Group, S. Navas, and others. Review of particle physics: Chapter on Machine Learning. Phys. Rev. D, 110(3):030001, 2024. doi:10.1103/PhysRevD.110.030001. [1817 citations] [DOI] [BibTeX] [show altmetrics]
  2. ★ Giuseppe Carleo, Ignacio Cirac, Kyle Cranmer, Laurent Daudet, Maria Schuld, and others. Machine learning and the physical sciences. Rev. Mod. Phys., 91(4):045002, 2019. arXiv:1903.10563, doi:10.1103/RevModPhys.91.045002. [2247 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  3. Dan Guest, Kyle Cranmer, and Daniel Whiteson. Deep Learning and its Application to LHC Physics. Ann. Rev. Nucl. Part. Sci., 68:161–181, 2018. arXiv:1806.11484, doi:10.1146/annurev-nucl-101917-021019. [369 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]

Statistics / Classical Machine Learning

Statistical methods and classical machine learning for particle physics.

  1. ★ Glen Cowan, Kyle Cranmer, Eilam Gross, and Ofer Vitells. Asymptotic formulae for likelihood-based tests of new physics. Eur. Phys. J. C, 71:1554, 2011. Erratum: Eur. Phys. J. C 73 (2013) 2501. arXiv:1007.1727, doi:10.1140/epjc/s10052-011-1554-0. [2706 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  2. Kyle S. Cranmer. Frequentist hypothesis testing with background uncertainty. eConf, C030908:WEMT004, 2003. arXiv:physics/0310108. [28 citations] [arXiv] [BibTeX] [show altmetrics]
  3. Kyle S. Cranmer. Multivariate analysis from a statistical point of view. 2003. arXiv:physics/0310110. [3 citations] [arXiv] [BibTeX] [show altmetrics]
  4. Kyle S. Cranmer. Statistics for the LHC: Progress, challenges, and future. 2008. doi:10.5170/CERN-2008-001.47. [8 citations] [DOI] [BibTeX] [show altmetrics]
  5. Kyle Cranmer. Statistical challenges for searches for new physics at the LHC. 2005. arXiv:physics/0511028, doi:10.1142/9781860948985_0026. [22 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  6. Kyle S. Cranmer. Kernel estimation in high-energy physics. Comput. Phys. Commun., 136:198–207, 2001. doi:10.1016/S0010-4655(00)00243-5. [482 citations] [DOI] [BibTeX] [show altmetrics]
  7. K. S. Cranmer, B. Mellado, W. Quayle, and Sau Lan Wu. Challenges in moving the LEP Higgs statistics to the LHC. eConf, C030908:MODT004, 2003. arXiv:physics/0312050. [9 citations] [arXiv] [BibTeX] [show altmetrics]
  8. Kyle Cranmer and R. Sean Bowman. PhysicsGP: A Genetic Programming Approach to Event Selection. Comput. Phys. Commun., 167:165–176, 2005. arXiv:physics/0402030, doi:10.1016/j.cpc.2004.12.006. [23 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  9. Kyle S. Cranmer. Multivariate analysis and the search for new particles. Acta Phys. Polon. B, 34:6049–6068, 2003. [BibTeX]

High-Energy Physics - Phenomenology

Theoretical and phenomenological studies in particle physics.

  1. Johann Brehmer, Kyle Cranmer, Irina Espejo, Felix Kling, Gilles Louppe, and others. Effective LHC measurements with matrix elements and machine learning. J. Phys. Conf. Ser., 1525(1):012022, 2020. arXiv:1906.01578, doi:10.1088/1742-6596/1525/1/012022. [19 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  2. Johann Brehmer, Kyle Cranmer, Felix Kling, and Tilman Plehn. Better Higgs boson measurements through information geometry. Phys. Rev. D, 95(7):073002, 2017. arXiv:1612.05261, doi:10.1103/PhysRevD.95.073002. [66 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  3. Ben C. Allanach, Kyle Cranmer, Christopher G. Lester, and Arne M. Weber. Natural priors, CMSSM fits and LHC weather forecasts. JHEP, 08:023, 2007. arXiv:0705.0487, doi:10.1088/1126-6708/2007/08/023. [92 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  4. Kyle Cranmer and Tilman Plehn. Maximum significance at the LHC and Higgs decays to muons. Eur. Phys. J. C, 51:415–420, 2007. arXiv:hep-ph/0605268, doi:10.1140/epjc/s10052-007-0309-4. [34 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  5. Michael Bridges, Kyle Cranmer, Farhan Feroz, Mike Hobson, and Roberto Ruiz de Austri. A Coverage Study of the CMSSM Based on ATLAS Sensitivity Using Fast Neural Networks. JHEP, 03:012, 2011. arXiv:1011.4306, doi:10.1007/JHEP03(2011)012. [38 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  6. K. Cranmer, Y. Q. Fang, B. Mellado, S. Paganis, W. Quayle, and others. Prospects for Higgs searches via VBF at the LHC with the ATLAS detector. 2004. arXiv:hep-ph/0401148. [6 citations] [arXiv] [BibTeX] [show altmetrics]

High-Energy Physics - Software and Infrastructure

Software tools and infrastructure for particle physics analysis.

  1. ATLAS Collaboration. An implementation of neural simulation-based inference for parameter estimation in ATLAS. 2024. arXiv:2412.01600. [arXiv] [BibTeX] [show altmetrics]
  2. Johann Brehmer, Felix Kling, Irina Espejo, and Kyle Cranmer. MadMiner: Machine learning-based inference for particle physics. Comput. Softw. Big Sci., 4(1):3, 2020. arXiv:1907.10621, doi:10.1007/s41781-020-0035-2. [129 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  3. Kyle Cranmer and Itay Yavin. RECAST: Extending the Impact of Existing Analyses. JHEP, 04:038, 2011. arXiv:1010.2506, doi:10.1007/JHEP04(2011)038. [70 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  4. Lorenzo Moneta, Kevin Belasco, Kyle S. Cranmer, S. Kreiss, Alfio Lazzaro, and others. The RooStats Project. PoS, ACAT2010:057, 2010. arXiv:1009.1003, doi:10.22323/1.093.0057. [228 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  5. ATLAS Collaboration and K. S. Cranmer. The ATLAS analysis architecture. Nucl. Phys. B Proc. Suppl., 177-178:126–130, 2008. doi:10.1016/j.nuclphysbps.2007.11.096. [9 citations] [DOI] [BibTeX] [show altmetrics]

High-Energy Physics - Experiment (selected highlights)

Selected experimental results from particle physics collaborations.

  1. ATLAS Collaboration. Measurement of off-shell Higgs boson production using neural simulation-based inference. 2024. arXiv:2412.01548. [arXiv] [BibTeX] [show altmetrics]
  2. Zubair Bhatti, Kyle Cranmer, Irina Espejo, Lukas Heinrich, Phillip Gadow, Patrick Rieck, and Janik von Ahne. Efficient Search for New Physics Using Active Learning in the ATLAS Experiment. EPJ Web Conf., 295:09013, 2024. doi:10.1051/epjconf/202429509013. [DOI] [BibTeX] [show altmetrics]
  3. ★ ATLAS Collaboration. Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC. Phys. Lett. B, 716:1–29, 2012. arXiv:1207.7214, doi:10.1016/j.physletb.2012.08.020. [10301 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  4. CDF Collaboration. Search for High Mass Resonances Decaying to Muon Pairs. Phys. Rev. Lett., 106:121801, 2011. arXiv:1101.4578, doi:10.1103/PhysRevLett.106.121801. [36 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]
  5. ALEPH Collaboration and Kyle Cranmer. Higgs To Four Taus At ALEPH. JHEP, 05:049, 2010. arXiv:1003.0705, doi:10.1007/JHEP05(2010)049. [66 citations] [arXiv] [DOI] [BibTeX] [show altmetrics]