{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T07:44:32Z","timestamp":1763365472425,"version":"3.45.0"},"reference-count":57,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100005156","name":"Alexander von Humboldt-Stiftung","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100005156","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"crossref","award":["200020_212127"],"award-info":[{"award-number":["200020_212127"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,12,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>We introduce a novel approach for end-to-end black-box optimization of high energy physics (HEP) detectors using local deep learning surrogates. These surrogates approximate a scalar objective function that encapsulates the complex interplay of particle-matter interactions and physics analysis goals. In addition to a standard reconstruction-based metric commonly used in the field, we investigate the information-theoretic metric of mutual information. In contrast to traditional methods, mutual information is inherently task-agnostic, offering a broader optimization paradigm that is less constrained by predefined targets. We demonstrate the effectiveness of our method in a realistic physics analysis scenario: optimizing the thicknesses of calorimeter detector layers based on simulated particle interactions. The surrogate model learns to approximate objective gradients, enabling efficient optimization with respect to energy resolution. Our findings reveal three key insights: (1) end-to-end black-box optimization using local surrogates is a practical and compelling approach for detector design, providing direct optimization of detector parameters in alignment with physics analysis goals; (2) mutual information-based optimization yields design choices that closely match those from state-of-the-art physics-informed methods, indicating that these approaches operate near optimality and reinforcing their reliability in HEP detector design; and (3) information-theoretic methods provide a powerful, generalizable framework for optimizing scientific instruments. By reframing the optimization process through an information-theoretic lens rather than domain-specific heuristics, mutual information enables the exploration of new avenues for discovery beyond conventional approaches.<\/jats:p>","DOI":"10.1088\/2632-2153\/ae1acb","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T22:53:03Z","timestamp":1762210383000},"page":"045047","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["End-to-end optimal detector design with mutual information surrogates"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4395-1581","authenticated-orcid":true,"given":"Kinga","family":"Anna Wo\u017aniak","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0310-9548","authenticated-orcid":true,"given":"Stephen","family":"Mulligan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1644-7678","authenticated-orcid":false,"given":"Jan","family":"Kieseler","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0869-5631","authenticated-orcid":false,"given":"Markus","family":"Klute","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9457-7393","authenticated-orcid":false,"given":"Fran\u00e7ois","family":"Fleuret","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8535-6687","authenticated-orcid":true,"given":"Tobias","family":"Golling","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2025,11,17]]},"reference":[{"key":"mlstae1acbbib1","doi-asserted-by":"crossref","DOI":"10.2172\/1767028","type":"other","article-title":"High-luminosity large Hadron collider (HL-LHC). Technical design report V. 0.1","author":"Apollinari","year":"2017"},{"key":"mlstae1acbbib2","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1140\/epjst\/e2019-900087-0","type":"journal-article","article-title":"FCC-HH: the Hadron collider: future circular collider conceptual design report volume 3","volume":"228","author":"The FCC Collaboration","year":"2019","journal-title":"Eur. Phys. J. Spec. Top."},{"key":"mlstae1acbbib3","doi-asserted-by":"publisher","DOI":"10.1016\/j.revip.2023.100085","type":"journal-article","article-title":"Toward the end-to-end optimization of particle physics instruments with differentiable programming","volume":"10","author":"Dorigo","year":"2023","journal-title":"Rev. Phys."},{"key":"mlstae1acbbib4","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1023\/A:1008306431147","type":"journal-article","article-title":"Efficient global optimization of expensive black-box functions","volume":"13","author":"Jones","year":"1998","journal-title":"J. Glob. Optim."},{"key":"mlstae1acbbib5","doi-asserted-by":"publisher","DOI":"10.1016\/j.physo.2025.100270","type":"journal-article","article-title":"On the utility function of experiments in fundamental science","volume":"23","author":"Dorigo","year":"2025","journal-title":"Phys. Open"},{"key":"mlstae1acbbib6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ACCESS.2024.3425448","type":"journal-article","article-title":"A review of differentiable simulators","volume":"PP","author":"Newbury","year":"2024","journal-title":"IEEE Access"},{"key":"mlstae1acbbib7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2024.109491","type":"journal-article","article-title":"Optimization using pathwise algorithmic derivatives of electromagnetic shower simulations","volume":"309","author":"Aehle","year":"2025","journal-title":"Comput. Phys. Commun."},{"key":"mlstae1acbbib8","doi-asserted-by":"publisher","DOI":"10.1016\/j.nuclphysb.2025.116934","type":"journal-article","article-title":"Toward the end-to-end optimization of the SWGO array layout","volume":"1017","author":"Dorigo","year":"2025","journal-title":"Nucl. Phys. B"},{"key":"mlstae1acbbib9","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1080\/10619127.2021.1881364","type":"journal-article","article-title":"Toward machine learning optimization of experimental design","volume":"31","author":"Baydin","year":"2021","journal-title":"Nucl. Phys. News"},{"key":"mlstae1acbbib10","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad52e7","type":"journal-article","article-title":"Tomopt: differential optimisation for task- and constraint-aware design of particle detectors in the context of muon tomography","volume":"5","author":"Strong","year":"2024","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstae1acbbib11","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevAccelBeams.28.034601","type":"journal-article","article-title":"Injection optimization at particle accelerators via reinforcement learning: from simulation to real-world application","volume":"28","author":"Awal","year":"2025","journal-title":"Phys. Rev. Accel. Beams"},{"key":"mlstae1acbbib12","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1038\/s41586-021-04301-9","type":"journal-article","article-title":"Magnetic control of tokamak plasmas through deep reinforcement learning","volume":"602","author":"Degrave","year":"2022","journal-title":"Nature"},{"article-title":"Black box optimization via a Bayesian-optimized genetic algorithm","year":"2017","author":"Golovin","key":"mlstae1acbbib13","type":"conference-proceedings"},{"key":"mlstae1acbbib14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevSTAB.16.010101","type":"journal-article","article-title":"Innovative applications of genetic algorithms to problems in accelerator physics","volume":"16","author":"Hofler","year":"2013","journal-title":"Phys. Rev. ST Accel. Beams"},{"key":"mlstae1acbbib15","doi-asserted-by":"publisher","DOI":"10.1063\/1.4808213","type":"journal-article","article-title":"Evolutionary optimization of an experimental apparatus","volume":"102","author":"Geisel","year":"2013","journal-title":"Appl. Phys. Lett."},{"key":"mlstae1acbbib16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.108.102002","type":"journal-article","article-title":"Using evolutionary algorithms to design antennas with greater sensitivity to ultrahigh energy neutrinos","volume":"108","author":"The GENETIS Collaboration","year":"2023","journal-title":"Phys. Rev. D"},{"key":"mlstae1acbbib17","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","type":"journal-article","article-title":"Taking the human out of the loop: a review of Bayesian optimization","volume":"104","author":"Shahriari","year":"2016","journal-title":"Proc. IEEE"},{"key":"mlstae1acbbib18","type":"conference-proceedings","article-title":"Scalable global optimization via local Bayesian optimization","volume":"vol 32","author":"Eriksson","year":"2019"},{"article-title":"The behavior and convergence of local Bayesian optimization","year":"2023","author":"Wu","key":"mlstae1acbbib19","type":"conference-proceedings"},{"article-title":"Local Bayesian optimization via maximizing probability of descent","year":"2022","author":"Nguyen","key":"mlstae1acbbib20","type":"conference-proceedings"},{"key":"mlstae1acbbib21","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1038\/s41598-020-60652-9","type":"journal-article","article-title":"Bayesian optimization for materials design with mixed quantitative and qualitative variables","volume":"10","author":"Zhang","year":"2020","journal-title":"Sci. Rep."},{"key":"mlstae1acbbib22","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1038\/s41524-023-01173-7","type":"journal-article","article-title":"A physics informed Bayesian optimization approach for material design: application to NiTi shape memory alloys","volume":"9","author":"Khatamsaz","year":"2023","journal-title":"npj Comput. Mater."},{"article-title":"Physics-informed Bayesian optimization of variational quantum circuits","year":"2023","author":"Nicoli","key":"mlstae1acbbib23","type":"conference-proceedings"},{"key":"mlstae1acbbib24","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109971","type":"journal-article","article-title":"Artificial intelligence driven laser parameter search: inverse design of photonic surfaces using greedy surrogate-based optimization","volume":"143","author":"Grbcic","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"mlstae1acbbib25","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrp.2020.100259","type":"journal-article","article-title":"Interpretable forward and inverse design of particle spectral emissivity using common machine-learning models","volume":"1","author":"Elzouka","year":"2020","journal-title":"Cell Rep. Phys. Sci."},{"key":"mlstae1acbbib26","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/17\/04\/C04038","type":"journal-article","article-title":"Design of detectors at the Electron Ion Collider with artificial intelligence","volume":"17","author":"Fanelli","year":"2022","journal-title":"J. Instrum."},{"key":"mlstae1acbbib27","doi-asserted-by":"publisher","DOI":"10.1016\/j.revip.2024.100092","type":"journal-article","article-title":"Deep generative models for detector signature simulation: a taxonomic review","volume":"12","author":"Hashemi","year":"2024","journal-title":"Rev. Phys."},{"key":"mlstae1acbbib28","first-page":"pp 14650","type":"conference-proceedings","article-title":"Black-box optimization with local generative surrogates","volume":"vol 33","author":"Shirobokov","year":"2020"},{"key":"mlstae1acbbib29","doi-asserted-by":"publisher","first-page":"47","DOI":"10.3390\/particles8020047","type":"journal-article","article-title":"End-to-end detector optimization with diffusion models: a case study in sampling calorimeters","volume":"8","author":"Schmidt","year":"2025","journal-title":"Particles"},{"article-title":"Bayesian algorithm execution: Estimating computable properties of black-box functions using mutual information","year":"2021","author":"Neiswanger","key":"mlstae1acbbib30","type":"conference-proceedings"},{"key":"mlstae1acbbib31","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1038\/s41524-024-01326-2","type":"journal-article","article-title":"Targeted materials discovery using Bayesian algorithm execution","volume":"10","author":"Chitturi","year":"2024","journal-title":"npj Comput. Mater."},{"year":"2002","author":"MacKay","key":"mlstae1acbbib32","type":"book"},{"year":"1999","author":"Cover","key":"mlstae1acbbib33","type":"book"},{"key":"mlstae1acbbib34","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006401","type":"journal-article","article-title":"Inferring interaction partners from protein sequences using mutual information","volume":"14","author":"Bitbol","year":"2018","journal-title":"PLoS Comput. Biol."},{"key":"mlstae1acbbib35","doi-asserted-by":"publisher","first-page":"1191","DOI":"10.1162\/089976603321780272","type":"journal-article","article-title":"Estimation of entropy and mutual information","volume":"15","author":"Paninski","year":"2003","journal-title":"Neural Comput."},{"key":"mlstae1acbbib36","first-page":"pp 49","type":"conference-proceedings","article-title":"Maximum mutual information estimation of hidden Markov parameters for speech recognition","volume":"vol 11","author":"Bahl","year":"1986"},{"key":"mlstae1acbbib37","first-page":"22","type":"journal-article","article-title":"Word association norms, mutual information and lexicography","volume":"16","author":"Church","year":"1990","journal-title":"Comput. Linguist."},{"key":"mlstae1acbbib38","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1016\/S0168-9002(03)01368-8","type":"journal-article","article-title":"Geant4-a simulation toolkit","volume":"506","author":"Agostinelli","year":"2003","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"mlstae1acbbib39","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1109\/TNS.2006.869826","type":"journal-article","article-title":"Geant4 developments and applications","volume":"53","author":"Allison","year":"2006","journal-title":"IEEE Trans. Nucl. Sci."},{"key":"mlstae1acbbib40","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1016\/j.nima.2016.06.125","type":"journal-article","article-title":"Recent developments in Geant4","volume":"835","author":"Allison","year":"2016","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"mlstae1acbbib41","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1016\/j.nima.2005.03.174","type":"journal-article","article-title":"A high resolution electromagnetic calorimeter based on lead-tungstate crystals","volume":"550","author":"Aleksandrov","year":"2005","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"mlstae1acbbib42","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/0168-9002(95)00589-7","type":"journal-article","article-title":"Lead tungstate (PbWO4) scintillators for LHCEM calorimetry","volume":"365","author":"Lecoq","year":"1995","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"mlstae1acbbib43","doi-asserted-by":"publisher","first-page":"20","DOI":"10.3389\/fphy.2023.1254020","type":"journal-article","article-title":"A highly-compact and ultra-fast homogeneous electromagnetic calorimeter based on oriented lead tungstate crystals","volume":"11","author":"Bandiera","year":"2023","journal-title":"Front. Phys."},{"key":"mlstae1acbbib44","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1137\/0719026","type":"journal-article","article-title":"Newton\u2019s method with a model trust region modification","volume":"19","author":"Sorensen","year":"1982","journal-title":"SIAM J. Numer. Anal."},{"key":"mlstae1acbbib45","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.69.066138","type":"journal-article","article-title":"Estimating mutual information","volume":"69","author":"Kraskov","year":"2004","journal-title":"Phys. Rev. E"},{"key":"mlstae1acbbib46","first-page":"pp 1530","type":"conference-proceedings","article-title":"Variational inference with normalizing flows","volume":"vol 37)","author":"Rezende","year":"2015"},{"key":"mlstae1acbbib47","doi-asserted-by":"publisher","first-page":"3964","DOI":"10.1109\/TPAMI.2020.2992934","type":"journal-article","article-title":"Normalizing flows: an introduction and review of current methods","volume":"43","author":"Kobyzev","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstae1acbbib48","first-page":"1","type":"journal-article","article-title":"Normalizing flows for probabilistic modeling and inference","volume":"22","author":"Papamakarios","year":"2021","journal-title":"J. Mach. Learn. Res."},{"article-title":"Learning likelihoods with conditional normalizing flows","year":"2023","author":"Winkler","key":"mlstae1acbbib49","type":"preprint"},{"key":"mlstae1acbbib50","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/3341156","type":"journal-article","article-title":"Neural importance sampling","volume":"38","author":"M\u00fcller","year":"2019","journal-title":"ACM Trans. Graph."},{"key":"mlstae1acbbib51","first-page":"pp 531","type":"conference-proceedings","article-title":"Mutual information neural estimation","volume":"vol 80)","author":"Belghazi","year":"2018"},{"article-title":"Learning deep representations by mutual information estimation and maximization","year":"2019","author":"Hjelm","key":"mlstae1acbbib52","type":"conference-proceedings"},{"key":"mlstae1acbbib53","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","type":"journal-article","article-title":"A comprehensive survey on transfer learning","volume":"109","author":"Zhuang","year":"2021","journal-title":"Proc. IEEE"},{"key":"mlstae1acbbib54","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.111.092015","type":"journal-article","article-title":"Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliders","volume":"111","author":"Mokhtar","year":"2025","journal-title":"Phys. Rev. D"},{"key":"mlstae1acbbib55","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/404\/1\/012002","type":"journal-article","article-title":"Role of the CMS electromagnetic calorimeter in the hunt for the Higgs boson in the two-gamma channel","volume":"404","author":"The CMS Collaboration","year":"2012","journal-title":"J. Phys.: Conf. Ser."},{"article-title":"Fast and accurate deep network learning by exponential linear units (elus)","year":"2016","author":"Clevert","key":"mlstae1acbbib56","type":"preprint"},{"year":"2017","author":"Kingma","key":"mlstae1acbbib57","type":"preprint"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1acb","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1acb\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1acb","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1acb\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1acb\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1acb\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1acb\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1acb\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T07:39:29Z","timestamp":1763365169000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1acb"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,17]]},"references-count":57,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,11,17]]},"published-print":{"date-parts":[[2025,12,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ae1acb","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2025,11,17]]},"assertion":[{"value":"End-to-end optimal detector design with mutual information surrogates","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-05-20","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-08-29","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-11-17","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}