{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:26:53Z","timestamp":1778048813006,"version":"3.51.4"},"reference-count":56,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2023,3,9]],"date-time":"2023-03-09T00:00:00Z","timestamp":1678320000000},"content-version":"vor","delay-in-days":323,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The celebrated Bernstein von-Mises theorem ensures credible regions from a Bayesian posterior to be well-calibrated when the model is correctly-specified, in the frequentist sense that their coverage probabilities tend to the nominal values as data accrue. However, this conventional Bayesian framework is known to lack robustness when the model is misspecified or partly specified, for example, in quantile regression, risk minimization based supervised\/unsupervised learning and robust estimation. To alleviate this limitation, we propose a new Bayesian inferential approach that substitutes the (misspecified or partly specified) likelihoods with proper exponentially tilted empirical likelihoods plus a regularization term. Our surrogate empirical likelihood is carefully constructed by using the first-order optimality condition of empirical risk minimization as the moment condition. We show that the Bayesian posterior obtained by combining this surrogate empirical likelihood and a prior is asymptotically close to a normal distribution centering at the empirical risk minimizer with an appropriate sandwich-form covariance matrix. Consequently, the resulting Bayesian credible regions are automatically calibrated to deliver valid uncertainty quantification. Computationally, the proposed method can be easily implemented by Markov Chain Monte Carlo sampling algorithms. Our numerical results show that the proposed method tends to be more accurate than existing state-of-the-art competitors.<\/jats:p>","DOI":"10.1111\/rssb.12510","type":"journal-article","created":{"date-parts":[[2022,4,21]],"date-time":"2022-04-21T02:21:05Z","timestamp":1650507665000},"page":"1257-1286","source":"Crossref","is-referenced-by-count":6,"title":["Bayesian Inference for Risk Minimization via Exponentially Tilted Empirical Likelihood"],"prefix":"10.1093","volume":"84","author":[{"given":"Rong","family":"Tang","sequence":"first","affiliation":[{"name":"Department of Statistics , Urbana , Illinois , USA"},{"name":"University of Illinois Urbana-Champaign , Urbana , Illinois , USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Statistics , Urbana , Illinois , USA"},{"name":"University of Illinois Urbana-Champaign , Urbana , Illinois , USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2022,4,20]]},"reference":[{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"279","DOI":"10.3103\/S1066530708040017","article-title":"PAC-Bayesian bounds for randomized empirical risk minimizers","volume":"17","author":"Alquier","year":"2008","journal-title":"Mathematical Methods of Statistics"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1162\/neco.1989.1.3.295","article-title":"Unsupervised learning","volume":"1","author":"Barlow","year":"1989","journal-title":"Neural Computation"},{"key":"2023030906301932400_","volume-title":"Gibbs posterior inference on multivariate quantiles","author":"Bhattacharya","year":"2020"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.1111\/rssb.12158","article-title":"A general framework for updating belief distributions","volume":"78","author":"Bissiri","year":"2016","journal-title":"Journal of the Royal Statistical Society. Series B, Statistical Methodology"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"2554","DOI":"10.1016\/j.jspi.2012.03.013","article-title":"Divergences and duality for estimation and test under moment condition models","volume":"142","author":"Broniatowski","year":"2012","journal-title":"Journal of Statistical Planning and Inference"},{"key":"2023030906301932400_","volume-title":"Empirical risk approximation: an induction principle for unsupervised learning","author":"Buhmann","year":"1998"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1093\/biomet\/asq017","article-title":"The horseshoe estimator for sparse signals","volume":"97","author":"Carvalho","year":"2010","journal-title":"Biometrika"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"1986","DOI":"10.1214\/15-AOS1334","article-title":"Bayesian linear regression with sparse priors","volume":"43","author":"Castillo","year":"2015","journal-title":"The Annals of Statistics"},{"key":"2023030906301932400_","first-page":"1","article-title":"PAC-Bayesian supervised classification: the thermodynamics of statistical learning","volume":"56","author":"Catoni","year":"2007","journal-title":"IMS Lecture Notes Monograph Series"},{"key":"2023030906301932400_","volume-title":"Advances in neural information processing systems","author":"Cauwenberghs","year":"1993"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1093\/biomet\/asm088","article-title":"Bayesian and frequentist confidence intervals arising from empirical-type likelihoods","volume":"95","author":"Chang","year":"2008","journal-title":"Biometrika"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1093\/biomet\/89.1.230","article-title":"Using empirical likelihood methods to obtain range restricted weights in regression estimators for surveys","volume":"89","author":"Chen","year":"2002","journal-title":"Biometrika"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/S0304-4076(03)00100-3","article-title":"An MCMC approach to classical estimation","volume":"115","author":"Chernozhukov","year":"2003","journal-title":"Journal of Econometrics"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"1656","DOI":"10.1080\/01621459.2017.1358172","article-title":"Bayesian estimation and comparison of moment condition models","volume":"113","author":"Chib","year":"2018","journal-title":"Journal of the American Statistical Association"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1023\/A:1013164120801","article-title":"On Bayesian model and variable selection using MCMC","volume":"12","author":"Dellaportas","year":"2002","journal-title":"Statistics and Computing"},{"key":"2023030906301932400_","volume-title":"Pattern classification","author":"Duda","year":"2012"},{"key":"2023030906301932400_","volume-title":"Empirical processes in M-estimation","author":"Geer","year":"2000"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1214\/ss\/1177011136","article-title":"Inference from iterative simulation using multiple sequences","volume":"7","author":"Gelman","year":"1992","journal-title":"Statistical Science"},{"key":"2023030906301932400_","volume-title":"Bayesian nonparametric","author":"Ghosh","year":"2003"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1214\/17-BA1085","article-title":"Inconsistency of Bayesian inference for misspecified linear models, and a proposal for repairing It","volume":"12","author":"Gr\u00fcnwald","year":"2017","journal-title":"Bayesian Analysis"},{"key":"2023030906301932400_","volume-title":"A primer on PAC-Bayesian learning","author":"Guedj","year":"2019"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","DOI":"10.1109\/ICDMW.2018.00174","volume-title":"Smoothed hinge loss and \u20181 support vector machines","author":"Hajewski","year":"2018"},{"key":"2023030906301932400_","first-page":"101","volume-title":"Linear methods for classification","author":"Hastie","year":"2009"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1007\/978-1-4612-4380-9_35","volume-title":"Breakthroughs in statistics","author":"Huber","year":"1992"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"730","DOI":"10.1214\/009053604000001147","article-title":"Spike and slab variable selection: frequentist and Bayesian strategies","volume":"33","author":"Ishwaran","year":"2005","journal-title":"The Annals of Statistics"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1214\/12-EJS675","article-title":"The Bernstein-von-Mises theorem under misspecification","volume":"6","author":"Kleijn","year":"2012","journal-title":"Electronic Journal of Statistics"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511754098","volume-title":"Quantile regression","author":"Koenker","year":"2005"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"33","DOI":"10.2307\/1913643","article-title":"Regression quantiles","volume":"46","author":"Koenker","year":"1978","journal-title":"Econometrica: Journal of the Econometric Society"},{"key":"2023030906301932400_","volume-title":"Information theory and statistics","author":"Kullback","year":"1997"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1093\/biomet\/90.2.319","article-title":"Bayesian empirical likelihood","volume":"90","author":"Lazar","year":"2003","journal-title":"Biometrika"},{"key":"2023030906301932400_","first-page":"1","article-title":"Empirical priors for prediction in sparse high-dimensional linear regression","volume":"21","author":"Martin","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"1822","DOI":"10.3150\/15-BEJ797","article-title":"Empirical bayes posterior concentration in sparse high-dimensional linear models","volume":"23","author":"Martin","year":"2017","journal-title":"Bernoulli"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","DOI":"10.1145\/307400.307435","volume-title":"PAC-Bayesian model averaging","author":"McAllester","year":"1999"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1111\/j.1467-9469.2009.00640.x","article-title":"Empirical likelihood for non-smooth criterion functions","volume":"36","author":"Molanes Lopez","year":"2009","journal-title":"Scandinavian Journal of Statistics"},{"key":"2023030906301932400_","first-page":"2111","volume-title":"Handbook of econometrics vol. 4 of handbook of econometrics","author":"Newey","year":"1986"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1214\/aos\/1176347494","article-title":"Empirical likelihood ratio confidence regions","volume":"18","author":"Owen","year":"1990","journal-title":"The Annals of Statistics"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1093\/biomet\/75.2.237","article-title":"Empirical likelihood ratio confidence intervals for a single functional","volume":"75","author":"Owen","year":"1988","journal-title":"Biometrika"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1214\/aos\/1176325370","article-title":"Empirical likelihood and general estimating equations","volume":"22","author":"Qin","year":"1994","journal-title":"The Annals of Statistics"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1111\/j.1467-9868.2010.00747.x","article-title":"Bayesian pseudo-empirical-likelihood intervals for complex surveys","volume":"72","author":"Rao","year":"2010","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"},{"key":"2023030906301932400_","volume-title":"High dimensional statistics","author":"Rigollet","year":"2015"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1214\/aoms\/1177729586","article-title":"A stochastic approximation method","volume":"22","author":"Robbins","year":"1951","journal-title":"Annals of Mathematical Statistics"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1007\/978-1-4615-7821-5_15","article-title":"Robust regression by means of S-estimators","author":"Rousseeuw","year":"1984","journal-title":"Robust and nonlinear time series analysis"},{"key":"2023030906301932400_","volume-title":"Robust regression and outlier detection","author":"Rousseeuw","year":"2005"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1093\/biomet\/92.1.31","article-title":"Bayesian exponentially tilted empirical likelihood","volume":"92","author":"Schennach","year":"2005","journal-title":"Biometrika"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"634","DOI":"10.1214\/009053606000001208","article-title":"Point estimation with exponentially tilted empirical likelihood","volume":"35","author":"Schennach","year":"2007","journal-title":"The Annals of Statistics"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1214\/13-BA817","article-title":"Posterior consistency of Bayesian quantile regression based on the Misspecified Asymmetric Laplace Density","volume":"8","author":"Sriram","year":"2013","journal-title":"Bayesian Analysis"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","DOI":"10.1109\/APCC47188.2019.9026527","volume-title":"Model-free unsupervised learning for optimization problems with constraints","author":"Sun","year":"2019"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1093\/biomet\/asy054","article-title":"Calibrating general posterior credible regions","volume":"106","author":"Syring","year":"2018","journal-title":"Biometrika"},{"key":"2023030906301932400_","volume-title":"Gibbs posterior concentration rates under sub-exponential type losses","author":"Syring","year":"2020"},{"key":"2023030906301932400_","volume-title":"Principles of risk minimization for learning theory","author":"Vapnik","year":"1991"},{"key":"2023030906301932400_","volume-title":"Introduction to robust estimation and hypothesis testing","author":"Wilcox","year":"2011"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1111\/insr.12097","article-title":"Calibration weighting methods for complex surveys","volume":"84","author":"Wu","year":"2016","journal-title":"International Statistical Review"},{"key":"2023030906301932400_","first-page":"2472","volume-title":"Proceedings of the 33rd International Conference on Machine Learning vol. 48 of Proceedings of Machine Learning Research","author":"Yang","year":"2016"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1016\/S0167-7152(01)00124-9","article-title":"Bayesian quantile regression","volume":"54","author":"Yu","year":"2001","journal-title":"Statistics and Probability Letters"},{"key":"2023030906301932400_","first-page":"233","article-title":"On assessing prior distributions and Bayesian regression analysis with g prior distributions. Bayesian inference and decision techniques: essays in Honor of Bruno de Finetti","volume":"6","author":"Zellner","year":"1986","journal-title":"Studies in Bayesian Econometrics and Statistics"},{"key":"2023030906301932400_","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1111\/rssb.12342","article-title":"Bayesian empirical likelihood inference with complex survey data","volume":"82","author":"Zhao","year":"2020","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"}],"container-title":["Journal of the Royal Statistical Society Series B: Statistical Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/rssb.12510","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/rssb.12510","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/84\/4\/1257\/49463267\/jrsssb_84_4_1257.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/84\/4\/1257\/49463267\/jrsssb_84_4_1257.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T08:10:48Z","timestamp":1700467848000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/article\/84\/4\/1257\/7073281"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,20]]},"references-count":56,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,4,20]]},"published-print":{"date-parts":[[2022,9,1]]}},"URL":"https:\/\/doi.org\/10.1111\/rssb.12510","relation":{},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,9]]},"published":{"date-parts":[[2022,4,20]]}}}