{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T16:35:51Z","timestamp":1764174951489,"version":"3.37.3"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,1,12]],"date-time":"2021-01-12T00:00:00Z","timestamp":1610409600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,1,12]],"date-time":"2021-01-12T00:00:00Z","timestamp":1610409600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comput Softw Big Sci"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Data analysis in science, e.g., high-energy particle physics, is often subject to an intractable likelihood if the observables and observations span a high-dimensional input space. Typically the problem is solved by reducing the dimensionality using feature engineering and histograms, whereby the latter allows to build the likelihood using Poisson statistics. However, in the presence of systematic uncertainties represented by nuisance parameters in the likelihood, an optimal dimensionality reduction with a minimal loss of information about the parameters of interest is not known. This work presents a novel strategy to construct the dimensionality reduction with neural networks for feature engineering and a differential formulation of histograms so that the full workflow can be optimized with the result of the statistical inference, e.g., the variance of a parameter of interest, as objective. We discuss how this approach results in an estimate of the parameters of interest that is close to optimal and the applicability of the technique is demonstrated with a simple example based on pseudo-experiments and a more complex example from high-energy particle physics.<\/jats:p>","DOI":"10.1007\/s41781-020-00049-5","type":"journal-article","created":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T13:02:32Z","timestamp":1610542952000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Optimal Statistical Inference in the Presence of Systematic Uncertainties Using Neural Network Optimization Based on Binned Poisson Likelihoods with Nuisance Parameters"],"prefix":"10.1007","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4485-2972","authenticated-orcid":false,"given":"Stefan","family":"Wunsch","sequence":"first","affiliation":[]},{"given":"Simon","family":"J\u00f6rger","sequence":"additional","affiliation":[]},{"given":"Roger","family":"Wolf","sequence":"additional","affiliation":[]},{"given":"G\u00fcnter","family":"Quast","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,1,12]]},"reference":[{"issue":"2","key":"49_CR1","doi-asserted-by":"publisher","first-page":"1554","DOI":"10.1140\/epjc\/s10052-011-1554-0","volume":"71","author":"G Cowan","year":"2011","unstructured":"Cowan G, Cranmer K, Gross E, Vitells O (2011) Asymptotic formulae for likelihood-based tests of new physics. Eur Phys J C 71(2):1554","journal-title":"Eur Phys J C"},{"key":"49_CR2","unstructured":"The ATLAS and CMS collaborations (2011) Procedure for the LHC Higgs boson search combination in summer 2011. Technical report, ATL-PHYS-PUB-2011-011, CMS NOTE 2011\/005"},{"key":"49_CR3","unstructured":"The CMS collaboration (2012) Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC. Phys Lett B 716(1):30"},{"key":"49_CR4","unstructured":"The ATLAS collaboration (2012) 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):1"},{"key":"49_CR5","doi-asserted-by":"crossref","unstructured":"Wunsch S, J\u00f6rger S, Wolf R, Quast G (2020) Reducing the dependence of the neural network function to systematic uncertainties in the input space. Comput Softw Big Sci, 4(1)","DOI":"10.1007\/s41781-020-00037-9"},{"key":"49_CR6","unstructured":"Conway JS (2011) Incorporating nuisance parameters in likelihoods for multisource spectra. arXiv preprint: arXiv:1103.0354"},{"issue":"5","key":"49_CR7","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1017\/S0305004100009580","volume":"22","author":"RA Fisher","year":"1925","unstructured":"Fisher RA (1925) Theory of statistical estimation. Math Proc Cambridge Philos Soc 22(5):700\u2013725","journal-title":"Math Proc Cambridge Philos Soc"},{"key":"49_CR8","volume-title":"Mathematical methods of statistics","author":"H Cram\u00e9r","year":"1999","unstructured":"Cram\u00e9r H (1999) Mathematical methods of statistics, vol 9. Princeton University Press, Princeton"},{"key":"49_CR9","doi-asserted-by":"crossref","unstructured":"Rao CR (1992) Information and the accuracy attainable in the estimation of statistical parameters. In: Breakthroughs in statistics. Springer, pp 235\u2013247","DOI":"10.1007\/978-1-4612-0919-5_16"},{"key":"49_CR10","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1016\/j.cpc.2019.06.007","volume":"244","author":"P De Castro","year":"2019","unstructured":"De Castro P, Dorigo T (2019) INFERNO: Inference-Aware Neural Optimisation. Comput Phys Commun 244:170\u2013179","journal-title":"Comput Phys Commun"},{"key":"49_CR11","unstructured":"Heinrich L, Simpson N (2020) pyhf\/neos: initial zenodo release. Zenodo"},{"key":"49_CR12","unstructured":"Elwood A, Kr\u00fccker D (2018) Direct optimisation of the discovery significance when training neural networks to search for new physics in particle colliders. arXiv preprint: arXiv:1806.00322"},{"issue":"8","key":"49_CR13","doi-asserted-by":"publisher","first-page":"083004","DOI":"10.1103\/PhysRevD.97.083004","volume":"97","author":"T Charnock","year":"2018","unstructured":"Charnock T, Lavaux G, Wandelt BD (2018) Automatic physical inference with information maximizing neural networks. Phys Rev D 97(8):083004","journal-title":"Phys Rev D"},{"key":"49_CR14","unstructured":"Louppe G et al (2017) Learning to pivot with adversarial networks. In: Advances in Neural Information Processing Systems. 982"},{"issue":"7","key":"49_CR15","doi-asserted-by":"publisher","first-page":"074034","DOI":"10.1103\/PhysRevD.96.074034","volume":"96","author":"C Shimmin","year":"2017","unstructured":"Shimmin C, Sadowski P, Baldi P, Weik E, Whiteson D, Goul E, S\u00f8gaard A (2017) Decorrelated jet substructure tagging using adversarial neural networks. Phys Rev D 96(7):074034","journal-title":"Phys Rev D"},{"key":"49_CR16","unstructured":"Estrade V, Germain C, Guyon I, Rousseau D (2018) Systematics aware learning: a case study in High Energy Physics. In: ESANN 2018 - 26th European Symposium on Artificial Neural Networks, Bruges, Belgium"},{"key":"49_CR17","doi-asserted-by":"crossref","unstructured":"Kasieczka G, Shih D (2020) Disco fever: Robust networks through distance correlation. arXiv preprint: arXiv:2001.05310","DOI":"10.1103\/PhysRevLett.125.122001"},{"key":"49_CR18","unstructured":"Cranmer K, Brehmer J, Louppe G (2019) The frontier of simulation-based inference. arXiv preprint: arXiv:1911.01429"},{"key":"49_CR19","unstructured":"Cranmer K, Pavez J, Louppe G (2015) Approximating likelihood ratios with calibrated discriminative classifiers. arXiv preprint: arXiv:1506.02169"},{"key":"49_CR20","unstructured":"Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics. pp 249\u2013256"},{"key":"49_CR21","unstructured":"Glorot X et al (2011) Deep sparse rectifier neural networks. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics. pp 315\u2013323"},{"key":"49_CR22","unstructured":"Abadi M, Agarwal A, Barham P et al (2016) Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint: arXiv:1603.04467"},{"key":"49_CR23","unstructured":"Dillon JV, Langmore I, Tran D, Brevdo E, Vasudevan S, Moore D, Patton B, Alemi A, Hoffman MD, Saurous RA (2017) Tensorflow distributions. CoRR arXiv:abs\/1711.10604"},{"key":"49_CR24","unstructured":"Kingma D, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint: arXiv:1412.6980"},{"key":"49_CR25","doi-asserted-by":"publisher","DOI":"10.1142\/6096","volume-title":"Statistical methods in experimental physics","author":"F James","year":"2006","unstructured":"James F (2006) Statistical methods in experimental physics. World Scientific Publishing Company, Singapore"},{"issue":"12","key":"49_CR26","doi-asserted-by":"publisher","first-page":"2499","DOI":"10.1016\/j.cpc.2009.08.005","volume":"180","author":"I Antcheva","year":"2009","unstructured":"Antcheva I, Ballintijn M, Bellenot B et al (2009) ROOT - A C++ framework for petabyte data storage, statistical analysis and visualization. Comput Phys Commun 180(12):2499\u20132512","journal-title":"Comput Phys Commun"},{"key":"49_CR27","doi-asserted-by":"crossref","unstructured":"Moneta L, Belasco K, Cranmer KS, Kreiss S, Lazzaro A, Piparo D, Schott G, Verkerke W, Wolf M (2010) The RooStats project. In: 13$$^\\text{th}$$ International Workshop on Advanced Computing and Analysis Techniques in Physics Research (ACAT2010), SISSA, PoS(ACAT2010)057","DOI":"10.22323\/1.093.0057"},{"key":"49_CR28","unstructured":"Verkerke W, Kirkby D (2003) The RooFit toolkit for data modeling"},{"key":"49_CR29","doi-asserted-by":"crossref","unstructured":"The CMS collaboration (2019) Search for $${\\rm t}\\overline{{\\rm t}}{\\rm H}$$ production in the $${\\rm H}\\rightarrow {\\rm b}\\overline{{\\rm b}}$$ decay channel with leptonic $${\\rm t}\\overline{{\\rm t}}$$ decays in proton-proton collisions at $$\\sqrt{s}=13$$ tev. JHEP 03:026","DOI":"10.1007\/JHEP03(2019)026"},{"key":"49_CR30","unstructured":"The CMS collaboration (2019) Measurement of Higgs boson production and decay to the $$\\tau \\tau$$ final state. CERN"},{"key":"49_CR31","unstructured":"Adam-Bourdarios C, Cowan G, Germain C, Guyon I, K\u00e9gl B, Rousseau D (2014) The Higgs boson machine learning challenge. In: HEPML@NIPS. 9\u201355"},{"key":"49_CR32","unstructured":"The ATLAS collaboration (2014) Dataset from the ATLAS Higgs Boson Machine Learning Challenge 2014. CERN Open Data Portal"}],"container-title":["Computing and Software for Big Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41781-020-00049-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41781-020-00049-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41781-020-00049-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,26]],"date-time":"2021-12-26T11:03:13Z","timestamp":1640516593000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41781-020-00049-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,12]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["49"],"URL":"https:\/\/doi.org\/10.1007\/s41781-020-00049-5","relation":{},"ISSN":["2510-2036","2510-2044"],"issn-type":[{"type":"print","value":"2510-2036"},{"type":"electronic","value":"2510-2044"}],"subject":[],"published":{"date-parts":[[2021,1,12]]},"assertion":[{"value":"5 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 December 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"4"}}