{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T11:38:53Z","timestamp":1784547533347,"version":"3.55.0"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2022,6,14]],"date-time":"2022-06-14T00:00:00Z","timestamp":1655164800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,2,11]]},"abstract":"<jats:title>Summary<\/jats:title>\n               <jats:p>Debiased machine learning is a meta-algorithm based on bias correction and sample splitting to calculate confidence intervals for functionals, i.e., scalar summaries, of machine learning algorithms. For example, an analyst may seek the confidence interval for a treatment effect estimated with a neural network. We present a non-asymptotic debiased machine learning theorem that encompasses any global or local functional of any machine learning algorithm that satisfies a few simple, interpretable conditions. Formally, we prove consistency, Gaussian approximation and semiparametric efficiency by finite-sample arguments. The rate of convergence is $n^{-1\/2}$ for global functionals, and it degrades gracefully for local functionals. Our results culminate in a simple set of conditions that an analyst can use to translate modern learning theory rates into traditional statistical inference. The conditions reveal a general double robustness property for ill-posed inverse problems.<\/jats:p>","DOI":"10.1093\/biomet\/asac033","type":"journal-article","created":{"date-parts":[[2022,6,14]],"date-time":"2022-06-14T13:39:00Z","timestamp":1655213940000},"page":"257-264","source":"Crossref","is-referenced-by-count":15,"title":["A simple and general debiased machine learning theorem with finite-sample guarantees"],"prefix":"10.1093","volume":"110","author":[{"given":"V","family":"Chernozhukov","sequence":"first","affiliation":[{"name":"Department of Economics, Massachusetts Institute of Technology , 50 Memorial Drive, Cambridge, Massachusetts 02142, U.S.A"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"W K","family":"Newey","sequence":"additional","affiliation":[{"name":"Department of Economics, Massachusetts Institute of Technology , 50 Memorial Drive, Cambridge, Massachusetts 02142, U.S.A"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9732-5001","authenticated-orcid":false,"given":"R","family":"Singh","sequence":"additional","affiliation":[{"name":"Department of Economics, Massachusetts Institute of Technology , 50 Memorial Drive, Cambridge, Massachusetts 02142, U.S.A"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,6,14]]},"reference":[{"key":"2023021111212077200_B1","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1080\/07350015.2014.975555","article-title":"Estimating conditional average treatment effects","volume":"33","author":"Abrevaya,","year":"2015","journal-title":"J. Bus. Econ. Statist."},{"key":"2023021111212077200_B2","doi-asserted-by":"crossref","first-page":"1795","DOI":"10.1111\/1468-0262.00470","article-title":"Efficient estimation of models with conditional moment restrictions containing unknown functions","volume":"71","author":"Ai,","year":"2003","journal-title":"Econometrica"},{"key":"2023021111212077200_B3","doi-asserted-by":"crossref","first-page":"43","DOI":"10.2307\/2951475","article-title":"Asymptotics for semiparametric econometric models via stochastic equicontinuity","volume":"62","author":"Andrews,","year":"1994","journal-title":"Econometrica"},{"key":"2023021111212077200_B4","doi-asserted-by":"publisher","DOI":"10.1080\/24709360.2021.1898730","article-title":"High-dimensional inference for the average treatment effect under model misspecification using penalized bias-reduced double-robust estimation","author":"Avagyan,","year":"2023","journal-title":"Biostatist. Epidemiol."},{"key":"2023021111212077200_B5","doi-asserted-by":"crossref","first-page":"2369","DOI":"10.3982\/ECTA9626","article-title":"Sparse models and methods for optimal instruments with an application to eminent domain","volume":"80","author":"Belloni,","year":"2012","journal-title":"Econometrica"},{"key":"2023021111212077200_B6","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1017\/CBO9781139060035.008","article-title":"Inference for high-dimensional sparse econometric models","volume-title":"Advances in Economics and Econometrics","author":"Belloni,","year":"2013"},{"key":"2023021111212077200_B7","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1093\/biomet\/asu056","article-title":"Uniform post-selection inference for least absolute deviation regression and other Z-estimation problems","volume":"102","author":"Belloni,","year":"2014","journal-title":"Biometrika"},{"key":"2023021111212077200_B8","article-title":"Data-adaptive smoothing for optimal-rate estimation of possibly non-regular parameters","author":"Bibaut,","year":"2017"},{"key":"2023021111212077200_B9","volume-title":"Efficient and Adaptive Estimation for Semiparametric Models","author":"Bickel,","year":"1993"},{"key":"2023021111212077200_B10","doi-asserted-by":"crossref","first-page":"1613","DOI":"10.1111\/j.1468-0262.2007.00808.x","article-title":"Semi-nonparametric IV estimation of shape-invariant Engel curves","volume":"75","author":"Blundell,","year":"2007","journal-title":"Econometrica"},{"key":"2023021111212077200_B11","doi-asserted-by":"publisher","DOI":"10.1515\/ijb-2017-0070","article-title":"Nonparametric bootstrap inference for the targeted highly adaptive least absolute shrinkage and selection operator (LASSO) estimator","volume":"16","author":"Cai,","year":"2020","journal-title":"Int. J. Biostatist."},{"key":"2023021111212077200_B12","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.3982\/ECTA13559","article-title":"Overidentification in regular models","volume":"86","author":"Chen,","year":"2018","journal-title":"Econometrica"},{"key":"2023021111212077200_B13","doi-asserted-by":"crossref","first-page":"C1","DOI":"10.1111\/ectj.12097","article-title":"Double\/debiased machine learning for treatment and structural parameters","volume":"21","author":"Chernozhukov,","year":"2018","journal-title":"Economet. J."},{"key":"2023021111212077200_B14","doi-asserted-by":"crossref","DOI":"10.3982\/ECTA16294","article-title":"Locally robust semiparametric estimation","author":"Chernozhukov,","year":"2022","journal-title":"Econometrica"},{"key":"2023021111212077200_B15","doi-asserted-by":"crossref","DOI":"10.1093\/ectj\/utac002","article-title":"Debiased machine learning of global and local parameters using regularized Riesz representers","author":"Chernozhukov,","year":"2022","journal-title":"Economet. J."},{"key":"2023021111212077200_B16","doi-asserted-by":"crossref","DOI":"10.3982\/ECTA18515","article-title":"Automatic debiased machine learning of causal and structural effects","author":"Chernozhukov,","year":"2022","journal-title":"Econometrica"},{"key":"2023021111212077200_B17","article-title":"Adversarial estimation of Riesz representers","author":"Chernozhukov,","year":"2020"},{"key":"2023021111212077200_B18","article-title":"Double debiased machine learning nonparametric inference with continuous treatments","author":"Colangelo,","year":"2021"},{"key":"2023021111212077200_B19","article-title":"Minimax estimation of conditional moment models","author":"Dikkala,","year":"2020"},{"key":"2023021111212077200_B20","article-title":"Orthogonal statistical learning","author":"Foster,","year":"2020"},{"key":"2023021111212077200_B21","first-page":"41","article-title":"On the nonparametric estimation of functionals","volume-title":"Proc. 2nd Prague Symp. on Asymptotic Statistics","author":"Hasminskii,","year":"1979"},{"key":"2023021111212077200_B22","doi-asserted-by":"crossref","DOI":"10.3982\/QE826","article-title":"The influence function of semiparametric estimators","author":"Ichimura,","year":"2022","journal-title":"Quant. Econ."},{"key":"2023021111212077200_B23","first-page":"2869","article-title":"Confidence intervals and hypothesis testing for high-dimensional regression","volume":"15","author":"Javanmard,","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"2023021111212077200_B24","article-title":"Causal inference under unmeasured confounding with negative controls: A minimax learning approach","author":"Kallus,","year":"2021"},{"key":"2023021111212077200_B25","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.1214\/aos\/1176350609","article-title":"Consistent estimation of the influence function of locally asymptotically linear estimators","volume":"15","author":"Klaassen,","year":"1987","journal-title":"Ann. Statist."},{"key":"2023021111212077200_B26","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1214\/15-AOS1384","article-title":"Statistical inference for the mean outcome under a possibly non-unique optimal treatment strategy","volume":"44","author":"Luedtke,","year":"2016","journal-title":"Ann. Statist."},{"key":"2023021111212077200_B27","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.2307\/2951752","article-title":"The asymptotic variance of semiparametric estimators","volume":"62","author":"Newey,","year":"1994","journal-title":"Econometrica"},{"key":"2023021111212077200_B28","doi-asserted-by":"crossref","first-page":"1565","DOI":"10.1111\/1468-0262.00459","article-title":"Instrumental variable estimation of nonparametric models","volume":"71","author":"Newey,","year":"2003","journal-title":"Econometrica"},{"key":"2023021111212077200_B29","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-5769-1","volume-title":"Contributions to a General Asymptotic Statistical Theory","author":"Pfanzagl,","year":"1982"},{"key":"2023021111212077200_B30","doi-asserted-by":"crossref","first-page":"2300","DOI":"10.3150\/20-BEJ1309","article-title":"Universal sieve-based strategies for efficient estimation using machine learning tools","volume":"27","author":"Qiu,","year":"2021","journal-title":"Bernoulli"},{"key":"2023021111212077200_B31","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1080\/01621459.1995.10476494","article-title":"Semiparametric efficiency in multivariate regression models with missing data","volume":"90","author":"Robins,","year":"1995","journal-title":"J. Am. Statist. Assoc."},{"key":"2023021111212077200_B32","doi-asserted-by":"crossref","first-page":"931","DOI":"10.2307\/1912705","article-title":"Root-$N$-consistent semiparametric regression","volume":"56","author":"Robinson,","year":"1988","journal-title":"Econometrica"},{"key":"2023021111212077200_B33","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1093\/biomet\/asaa054","article-title":"Characterization of parameters with a mixed bias property","volume":"108","author":"Rotnitzky,","year":"2021","journal-title":"Biometrika"},{"key":"2023021111212077200_B34","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1016\/j.jeconom.2012.05.018","article-title":"Efficiency bounds for estimating linear functionals of nonparametric regression models with endogenous regressors","volume":"170","author":"Severini,","year":"2012","journal-title":"J. Economet."},{"key":"2023021111212077200_B35","article-title":"On the absolute constants in the Berry-Esseen type inequalities for identically distributed summands","author":"Shevtsova,","year":"2011"},{"key":"2023021111212077200_B36","article-title":"Debiased kernel methods","author":"Singh,","year":"2021"},{"key":"2023021111212077200_B37","first-page":"4593","article-title":"Kernel instrumental variable regression","volume-title":"Proc. 33rd Int. Conf. Neural Information Processing Systems (NeurIPS 2019)","author":"Singh,","year":"2019"},{"key":"2023021111212077200_B38","article-title":"A unifying approach for doubly-robust $\\ell_1$ regularized estimation of causal contrasts","author":"Smucler,","year":"2019"},{"key":"2023021111212077200_B39","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.1214\/14-AOS1221","article-title":"On asymptotically optimal confidence regions and tests for high-dimensional models","volume":"42","author":"Van de Geer,","year":"2014","journal-title":"Ann. Statist."},{"key":"2023021111212077200_B40","article-title":"Finite sample inference for targeted learning","author":"van der Laan,","year":"2017"},{"key":"2023021111212077200_B41","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-65304-4","volume-title":"Targeted Learning in Data Science","author":"van der Laan,","year":"2018"},{"key":"2023021111212077200_B42","doi-asserted-by":"publisher","DOI":"10.2202\/1557-4679.1043","article-title":"Targeted maximum likelihood learning","volume":"2","author":"van der Laan,","year":"2006","journal-title":"Int. J. Biostatist."},{"key":"2023021111212077200_B43","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1111\/rssb.12026","article-title":"Confidence intervals for low dimensional parameters in high dimensional linear models","volume":"76","author":"Zhang,","year":"2014","journal-title":"J. R. Statist. Soc. B"},{"key":"2023021111212077200_B44","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1007\/978-1-4419-9782-1_27","article-title":"Cross-validated targeted minimum-loss-based estimation","volume-title":"Targeted Learning","author":"Zheng,","year":"2011"}],"container-title":["Biometrika"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biomet\/advance-article-pdf\/doi\/10.1093\/biomet\/asac033\/45291101\/asac033.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/110\/1\/257\/49160070\/asac033.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/110\/1\/257\/49160070\/asac033.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,11]],"date-time":"2023-02-11T11:21:54Z","timestamp":1676114514000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biomet\/article\/110\/1\/257\/6608087"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,14]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,6,14]]},"published-print":{"date-parts":[[2023,2,11]]}},"URL":"https:\/\/doi.org\/10.1093\/biomet\/asac033","relation":{},"ISSN":["0006-3444","1464-3510"],"issn-type":[{"value":"0006-3444","type":"print"},{"value":"1464-3510","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,3,1]]},"published":{"date-parts":[[2022,6,14]]}}}