{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T21:51:35Z","timestamp":1791323495286,"version":"4.3.1"},"reference-count":91,"publisher":"Institute of Mathematical Statistics","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Ann. Statist."],"published-print":{"date-parts":[[2026,8,1]]},"abstract":"We propose using a modified conductance-based method to study the mixing time of an important class of two-block Gibbs samplers, the data augmentation (DA) algorithm. Using this method, we prove the first non-asymptotic polynomial upper bounds on mixing times of three important DA algorithms: DA algorithms for Bayesian Probit regression (ProbitDA) and Bayesian Logit regression (LogitDA), and Bayesian Lasso Regression (LassoDA). Concretely, for ProbitDA and LogitDA, we demonstrate a tight bound that explicitly depends on the design matrix and prior covariance matrix. Under the assumption that data are independently generated from either a sub-Gaussian or log-concave distribution and properly scaled, the bound implies that with \u03b7-warm start, parameter dimension d, and sample size n, with high probability over data, the two algorithms require O(nlog( log\u03b7 \u03f5)) steps to obtain samples with at most \u03f5 error in TV, KL or \u03c72 distance. Meanwhile, we show that under minimal data assumptions, LassoDA requires O(d2(dlogd+nlogn)2log(\u03b7 \u03f5)) steps to achieve \u03f5-accuracy in TV distance. The results are generally applicable to settings with large n and large d, including settings with highly imbalanced response data in Probit and Logit regression. We compare them with the best known guarantees of Langevin Monte Carlo and Metropolis Adjusted Langevin Algorithm. We evaluate our theoretical results using numerical examples, and discuss the mixing times of the three algorithms under feasible initialization.<\/jats:p>","DOI":"10.1214\/26-aos2641","type":"journal-article","created":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T08:19:56Z","timestamp":1787041196000},"page":"2083-2109","source":"Crossref","is-referenced-by-count":0,"title":["Fast mixing of data augmentation algorithms: Bayesian probit, logit and lasso regression"],"prefix":"10.1214","volume":"54","author":[{"given":"Holden","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Applied Mathematics and Statistics, Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kexin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics and Statistics, Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"108","reference":[{"key":"75","doi-asserted-by":"crossref","unstructured":"Rosenthal, J. S.<\/small> (1995). Minorization conditions and convergence rates for Markov chain Monte Carlo. J. Amer. Statist. Assoc.<\/i> 90<\/b> 558\u2013566.","DOI":"10.1080\/01621459.1995.10476548"},{"key":"3","doi-asserted-by":"crossref","unstructured":"Albert, J. H.<\/small> and Chib, S.<\/small> (1993). Bayesian analysis of binary and polychotomous response data. J. Amer. Statist. Assoc.<\/i> 88<\/b> 669\u2013679.","DOI":"10.1080\/01621459.1993.10476321"},{"key":"15","unstructured":"Chen, Y.<\/small>, Dwivedi, R.<\/small>, Wainwright, M. J.<\/small> and Yu, B.<\/small> (2020). Fast mixing of metropolized Hamiltonian Monte Carlo: Benefits of multi-step gradients. J. Mach. Learn. Res.<\/i> 21<\/b> Paper No. 92."},{"key":"35","doi-asserted-by":"publisher","unstructured":"Holley, R.<\/small> and Stroock, D.<\/small> (1987). Logarithmic Sobolev inequalities and stochastic Ising models. J. Stat. Phys.<\/i> 46<\/b> 1159\u20131194.","DOI":"10.1007\/BF01011161"},{"key":"38","doi-asserted-by":"publisher","unstructured":"JOHNDROW, J. E.<\/small>, SMITH, A.<\/small>, PILLAI, N.<\/small> and DUNSON, D. B.<\/small> (2019). MCMC for imbalanced categorical data. J. Amer. Statist. Assoc.<\/i> 114<\/b> 1394\u20131403.","DOI":"10.1080\/01621459.2018.1505626"},{"key":"70","doi-asserted-by":"publisher","unstructured":"QIN, Q.<\/small> and HOBERT, J. P.<\/small> (2021). On the limitations of single-step drift and minorization in Markov chain convergence analysis. Ann. Appl. Probab.<\/i> 31<\/b> 1633\u20131659.","DOI":"10.1214\/20-AAP1628"},{"key":"74","doi-asserted-by":"publisher","unstructured":"ROBERTS, G. O.<\/small> and ROSENTHAL, J. S.<\/small> (2001). Markov chains and de-initializing processes. Scand. J. Stat.<\/i> 28<\/b> 489\u2013504.","DOI":"10.1111\/1467-9469.00250"},{"key":"76","doi-asserted-by":"publisher","unstructured":"ROY, V.<\/small> and HOBERT, J. P.<\/small> (2007). Convergence rates and asymptotic standard errors for Markov chain Monte Carlo algorithms for Bayesian probit regression. J. R. Stat. Soc. Ser. B. Stat. Methodol.<\/i> 69<\/b> 607\u2013623.","DOI":"10.1111\/j.1467-9868.2007.00602.x"},{"key":"9","doi-asserted-by":"publisher","unstructured":"BOBKOV, S. G.<\/small> (1999). Isoperimetric and analytic inequalities for log-concave probability measures. Ann. Probab.<\/i> 27<\/b> 1903\u20131921.","DOI":"10.1214\/aop\/1022874820"},{"key":"56","doi-asserted-by":"publisher","unstructured":"LOV\u00c1SZ, L.<\/small> and VEMPALA, S.<\/small> (2007). The geometry of logconcave functions and sampling algorithms. Random Structures Algorithms<\/i> 30<\/b> 307\u2013358.","DOI":"10.1002\/rsa.20135"},{"key":"62","doi-asserted-by":"publisher","unstructured":"MILMAN, E.<\/small> and SODIN, S.<\/small> (2008). An isoperimetric inequality for uniformly log-concave measures and uniformly convex bodies. J. Funct. Anal.<\/i> 254<\/b> 1235\u20131268.","DOI":"10.1016\/j.jfa.2007.12.002"},{"key":"12","doi-asserted-by":"publisher","unstructured":"CATTIAUX, P.<\/small> and GUILLIN, A.<\/small> (2020). On the Poincar\u00e9 constant of log-concave measures. In Geometric Aspects of Functional Analysis. Vol. I<\/i>. Lecture Notes in Math.<\/i> 2256<\/b> 171\u2013217. Springer, Cham.","DOI":"10.1007\/978-3-030-36020-7_9"},{"key":"91","doi-asserted-by":"publisher","unstructured":"ZHANG, Z.<\/small>, SINHA, S.<\/small>, MAITI, T.<\/small> and SHIPP, E.<\/small> (2018). Bayesian variable selection in the accelerated failure time model with an application to the surveillance, epidemiology, and end results breast cancer data. Stat. Methods Med. Res.<\/i> 27<\/b> 971\u2013990.","DOI":"10.1177\/0962280215626947"},{"key":"29","doi-asserted-by":"publisher","unstructured":"FR\u00dcHWIRTH-SCHNATTER, S.<\/small> and FR\u00dcHWIRTH, R.<\/small> (2007). Auxiliary mixture sampling with applications to logistic models. Comput. Statist. Data Anal.<\/i> 51<\/b> 3509\u20133528.","DOI":"10.1016\/j.csda.2006.10.006"},{"key":"2","doi-asserted-by":"publisher","unstructured":"ADAMCZAK, R.<\/small>, LITVAK, A. E.<\/small>, PAJOR, A.<\/small> and TOMCZAK-JAEGERMANN, N.<\/small> (2011). Sharp bounds on the rate of convergence of the empirical covariance matrix. C. R. Math. Acad. Sci. Paris<\/i> 349<\/b> 195\u2013200.","DOI":"10.1016\/j.crma.2010.12.014"},{"key":"37","doi-asserted-by":"publisher","unstructured":"JERRUM, M.<\/small> and SINCLAIR, A.<\/small> (1989). Approximating the permanent. SIAM J. Comput.<\/i> 18<\/b> 1149\u20131178.","DOI":"10.1137\/0218077"},{"key":"17","doi-asserted-by":"publisher","unstructured":"CHOI, H. M.<\/small> and HOBERT, J. P.<\/small> (2013). The Polya-gamma Gibbs sampler for Bayesian logistic regression is uniformly ergodic. Electron. J. Stat.<\/i> 7<\/b> 2054\u20132064.","DOI":"10.1214\/13-EJS837"},{"key":"44","doi-asserted-by":"publisher","unstructured":"KHARE, K.<\/small> and HOBERT, J. P.<\/small> (2013). Geometric ergodicity of the Bayesian lasso. Electron. J. Stat.<\/i> 7<\/b> 2150\u20132163.","DOI":"10.1214\/13-EJS841"},{"key":"55","doi-asserted-by":"publisher","unstructured":"LOV\u00c1SZ, L.<\/small> and VEMPALA, S.<\/small> (2004). Hit-and-run from a corner. In Proceedings of the<\/i> 36th Annual ACM Symposium on Theory of Computing<\/i> 310\u2013314. ACM, New York.","DOI":"10.1145\/1007352.1007403"},{"key":"69","doi-asserted-by":"publisher","unstructured":"QIN, Q.<\/small> and HOBERT, J. P.<\/small> (2019). Convergence complexity analysis of Albert and Chib\u2019s algorithm for Bayesian probit regression. Ann. Statist.<\/i> 47<\/b> 2320\u20132347.","DOI":"10.1214\/18-AOS1749"},{"key":"33","doi-asserted-by":"publisher","unstructured":"HANS, C.<\/small> (2009). Bayesian lasso regression. Biometrika<\/i> 96<\/b> 835\u2013845.","DOI":"10.1093\/biomet\/asp047"},{"key":"79","doi-asserted-by":"publisher","unstructured":"Simpson, D.<\/small>, Rue, H.<\/small>, Riebler, A.<\/small>, Martins, T. G.<\/small> and S\u00d8rbye, S. H.<\/small> (2017). Penalising model component complexity: A principled, practical approach to constructing priors. Statist. Sci.<\/i> 32<\/b> 1\u201328.","DOI":"10.1214\/16-STS576"},{"key":"51","doi-asserted-by":"publisher","unstructured":"Liu, J. S.<\/small>, Wong, W. H.<\/small> and Kong, A.<\/small> (1994). Covariance structure of the Gibbs sampler with applications to the comparisons of estimators and augmentation schemes. Biometrika<\/i> 81<\/b> 27\u201340.","DOI":"10.1093\/biomet\/81.1.27"},{"key":"28","doi-asserted-by":"publisher","unstructured":"ELDAN, R.<\/small> (2013). Thin shell implies spectral gap up to polylog via a stochastic localization scheme. Geom. Funct. Anal.<\/i> 23<\/b> 532\u2013569.","DOI":"10.1007\/s00039-013-0214-y"},{"key":"36","doi-asserted-by":"publisher","unstructured":"HOLMES, C. C.<\/small> and HELD, L.<\/small> (2006). Bayesian auxiliary variable models for binary and multinomial regression. Bayesian Anal.<\/i> 1<\/b> 145\u2013168.","DOI":"10.1214\/06-BA105"},{"key":"50","doi-asserted-by":"publisher","unstructured":"Levin, D. A.<\/small> and Peres, Y.<\/small> (2017). Markov Chains and Mixing Times<\/i>. Amer. Math. Soc., Providence, RI.","DOI":"10.1090\/mbk\/107"},{"key":"1","doi-asserted-by":"publisher","unstructured":"Adamczak, R.<\/small>, Litvak, A. E.<\/small>, Pajor, A.<\/small> and Tomczak-Jaegermann, N.<\/small> (2010). Quantitative estimates of the convergence of the empirical covariance matrix in log-concave ensembles. J. Amer. Math. Soc.<\/i> 23<\/b> 535\u2013561.","DOI":"10.1090\/S0894-0347-09-00650-X"},{"key":"27","doi-asserted-by":"publisher","unstructured":"Dyer, M.<\/small>, Frieze, A.<\/small> and Kannan, R.<\/small> (1991). A random polynomial-time algorithm for approximating the volume of convex bodies. J. Assoc. Comput. Mach.<\/i> 38<\/b> 1\u201317.","DOI":"10.1145\/102782.102783"},{"key":"67","doi-asserted-by":"publisher","unstructured":"Park, T.<\/small> and Casella, G.<\/small> (2008). The Bayesian lasso. J. Amer. Statist. Assoc.<\/i> 103<\/b> 681\u2013686.","DOI":"10.1198\/016214508000000337"},{"key":"34","doi-asserted-by":"crossref","unstructured":"Hobert, J. P.<\/small> (2011). The data augmentation algorithm: Theory and methodology. In Handbook of Markov Chain Monte Carlo<\/i>. Chapman & Hall\/CRC Handb. Mod. Stat. Methods<\/i> 253\u2013293. CRC Press, Boca Raton, FL.","DOI":"10.1201\/b10905-11"},{"key":"39","doi-asserted-by":"publisher","unstructured":"Jones, G. L.<\/small> and Hobert, J. P.<\/small> (2001). Honest exploration of intractable probability distributions via Markov chain Monte Carlo. Statist. Sci.<\/i> 16<\/b> 312\u2013334.","DOI":"10.1214\/ss\/1015346317"},{"key":"87","doi-asserted-by":"publisher","unstructured":"Vershynin, R.<\/small> (2018). High-Dimensional Probability<\/i>: An Introduction with Applications in Data Science<\/i>. Cambridge Series in Statistical and Probabilistic Mathematics<\/i> 47<\/b>. Cambridge Univ. Press, Cambridge.","DOI":"10.1017\/9781108231596"},{"key":"68","doi-asserted-by":"publisher","unstructured":"Polson, N. G.<\/small>, Scott, J. G.<\/small> and Windle, J.<\/small> (2013). Bayesian inference for logistic models using P\u00f3lya-Gamma latent variables. J. Amer. Statist. Assoc.<\/i> 108<\/b> 1339\u20131349.","DOI":"10.1080\/01621459.2013.829001"},{"key":"83","doi-asserted-by":"crossref","unstructured":"Tanner, M. A.<\/small> and Wong, W. H.<\/small> (1987). The calculation of posterior distributions by data augmentation. J. Amer. Statist. Assoc.<\/i> 82<\/b> 528\u2013550.","DOI":"10.1080\/01621459.1987.10478458"},{"key":"26","unstructured":"DWIVEDI, R.<\/small>, CHEN, Y.<\/small>, WAINWRIGHT, M. J.<\/small> and YU, B.<\/small> (2019). Log-concave sampling: Metropolis\u2013Hastings algorithms are fast. J. Mach. Learn. Res.<\/i> 20<\/b> Paper No. 183."},{"key":"58","doi-asserted-by":"publisher","unstructured":"MANGOUBI, O.<\/small> and SMITH, A.<\/small> (2021). Mixing of Hamiltonian Monte Carlo on strongly log-concave distributions: Continuous dynamics. Ann. Appl. Probab.<\/i> 31<\/b> 2019\u20132045.","DOI":"10.1214\/20-aap1640"},{"key":"61","doi-asserted-by":"publisher","unstructured":"MILMAN, E.<\/small> (2012). Properties of isoperimetric, functional and transport-entropy inequalities via concentration. Probab. Theory Related Fields<\/i> 152<\/b> 475\u2013507.","DOI":"10.1007\/s00440-010-0328-1"},{"key":"53","doi-asserted-by":"publisher","unstructured":"LOV\u00c1SZ, L.<\/small> and SIMONOVITS, M.<\/small> (1993). Random walks in a convex body and an improved volume algorithm. Random Structures Algorithms<\/i> 4<\/b> 359\u2013412.","DOI":"10.1002\/rsa.3240040402"},{"key":"71","doi-asserted-by":"publisher","unstructured":"QIN, Q.<\/small> and HOBERT, J. P.<\/small> (2022). Wasserstein-based methods for convergence complexity analysis of MCMC with applications. Ann. Appl. Probab.<\/i> 32<\/b> 124\u2013166.","DOI":"10.1214\/21-aap1673"},{"key":"72","unstructured":"RAJARATNAM, B.<\/small> and SPARKS, D.<\/small> (2015). MCMC-based inference in the era of big data: A fundamental analysis of the convergence complexity of high-dimensional chains. arXiv preprint. Available at arXiv:1508.00947<\/a>."},{"key":"25","doi-asserted-by":"publisher","unstructured":"DVORZAK, M.<\/small> and WAGNER, H.<\/small> (2016). Sparse Bayesian modelling of underreported count data. Stat. Model.<\/i> 16<\/b> 24\u201346.","DOI":"10.1177\/1471082X15588398"},{"key":"10","doi-asserted-by":"publisher","unstructured":"BOBKOV, S. G.<\/small> and HOUDR\u00c9, C.<\/small> (1997). Isoperimetric constants for product probability measures. Ann. Probab.<\/i> 25<\/b> 184\u2013205.","DOI":"10.1214\/aop\/1024404284"},{"key":"23","doi-asserted-by":"crossref","unstructured":"DIEBOLT, J.<\/small> and ROBERT, C. P.<\/small> (1994). Estimation of finite mixture distributions through Bayesian sampling. J. Roy. Statist. Soc. Ser. B, Methodol.<\/i> 56<\/b> 363\u2013375.","DOI":"10.1111\/j.2517-6161.1994.tb01985.x"},{"key":"84","doi-asserted-by":"crossref","unstructured":"TIBSHIRANI, R.<\/small> (1996). Regression shrinkage and selection via the lasso. J. Roy. Statist. Soc. Ser. B, Methodol.<\/i> 58<\/b> 267\u2013288.","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"52","doi-asserted-by":"publisher","unstructured":"LOV\u00c1SZ, L.<\/small> (1999). Hit-and-run mixes fast. Math. Program.<\/i> 86<\/b> 443\u2013461.","DOI":"10.1007\/s101070050099"},{"key":"24","doi-asserted-by":"publisher","unstructured":"DURANTE, D.<\/small> and DUNSON, D. B.<\/small> (2018). Bayesian inference and testing of group differences in brain networks. Bayesian Anal.<\/i> 13<\/b> 29\u201358.","DOI":"10.1214\/16-BA1030"},{"key":"4","doi-asserted-by":"publisher","unstructured":"ALONSO-GUTI\u00c9RREZ, D.<\/small> and BASTERO, J.<\/small> (2015). Approaching the Kannan-Lov\u00e1sz-Simonovits and Variance Conjectures<\/i>. Lecture Notes in Math.<\/i> 2131<\/b>. Springer, Cham.","DOI":"10.1007\/978-3-319-13263-1"},{"key":"5","doi-asserted-by":"crossref","unstructured":"ANDREWS, D. F.<\/small> and MALLOWS, C. L.<\/small> (1974). Scale mixtures of normal distributions. J. Roy. Statist. Soc. Ser. B, Methodol.<\/i> 36<\/b> 99\u2013102.","DOI":"10.1111\/j.2517-6161.1974.tb00989.x"},{"key":"6","unstructured":"ASCOLANI, F.<\/small>, LAVENANT, H.<\/small> and ZANELLA, G.<\/small> (2024). Entropy contraction of the Gibbs sampler under log-concavity. arXiv Preprint. Available at arXiv:2410.00858<\/a>."},{"key":"7","unstructured":"BARTHE, F.<\/small> and KLARTAG, B.<\/small> (2020). Spectral gaps, symmetries and log-concave perturbations. Bull. Hellenic Math. Soc.<\/i> 64<\/b> 1\u201331."},{"key":"8","doi-asserted-by":"publisher","unstructured":"BARTHE, F.<\/small> and MILMAN, E.<\/small> (2013). Transference principles for log-Sobolev and spectral-gap with applications to conservative spin systems. Comm. Math. Phys.<\/i> 323<\/b> 575\u2013625.","DOI":"10.1007\/s00220-013-1782-2"},{"key":"14","unstructured":"CHEN, Y.<\/small>, DWIVEDI, R.<\/small>, WAINWRIGHT, M. J.<\/small> and YU, B.<\/small> (2018). Fast MCMC sampling algorithms on polytopes. J. Mach. Learn. Res.<\/i> 19<\/b> Paper No. 55."},{"key":"16","unstructured":"CHEWI, S.<\/small> (2023). Log-concave sampling. Book Draft Available at https:\/\/chewisinho.github.io<\/a>."},{"key":"18","doi-asserted-by":"crossref","unstructured":"COHEN, A.<\/small> and EINAV, L.<\/small> (2007). Estimating risk preferences from deductible choice. Amer. Econ. Rev.<\/i> 97<\/b> 745\u2013788.","DOI":"10.1257\/aer.97.3.745"},{"key":"19","doi-asserted-by":"publisher","unstructured":"COURTADE, T. A.<\/small> (2020). Bounds on the Poincar\u00e9 constant for convolution measures. Ann. Inst. Henri Poincar\u00e9 Probab. Stat.<\/i> 56<\/b> 566\u2013579.","DOI":"10.1214\/19-AIHP973"},{"key":"20","doi-asserted-by":"publisher","unstructured":"COUSINS, B.<\/small> and VEMPALA, S.<\/small> (2014). A cubic algorithm for computing Gaussian volume. In Proceedings of the Twenty-Fifth Annual ACM-SIAM Symposium on Discrete Algorithms<\/i> 1215\u20131228. ACM, New York.","DOI":"10.1137\/1.9781611973402.90"},{"key":"21","unstructured":"DAI, Y.<\/small>, GAO, Y.<\/small>, HUANG, J.<\/small>, JIAO, Y.<\/small>, KANG, L.<\/small> and LIU, J.<\/small> (2023). Lipschitz Transport Maps via the Follmer Flow. arXiv Preprint. Available at arXiv:2309.03490<\/a>."},{"key":"22","unstructured":"DALALYAN, A.<\/small> (2017). Further and stronger analogy between sampling and optimization: Langevin Monte Carlo and gradient descent. In Conference on Learning Theory<\/i> 678\u2013689. PMLR."},{"key":"30","doi-asserted-by":"publisher","unstructured":"FUGLSTAD, G.-A.<\/small>, HEM, I. G.<\/small>, KNIGHT, A.<\/small>, RUE, H.<\/small> and RIEBLER, A.<\/small> (2020). Intuitive joint priors for variance parameters. Bayesian Anal.<\/i> 15<\/b> 1109\u20131137.","DOI":"10.1214\/19-BA1185"},{"key":"31","unstructured":"GRANT, E. H. C.<\/small>, MILLER, D. A.<\/small>, SCHMIDT, B. R.<\/small>, ADAMS, M. J.<\/small>, AMBURGEY, S. M.<\/small>, CHAMBERT, T.<\/small>, CRUICKSHANK, S. S.<\/small>, FISHER, R. N.<\/small>, GREEN, D. M.<\/small> et al. (2016). Quantitative evidence for the effects of multiple drivers on continental-scale amphibian declines. Sci. Rep.<\/i> 6<\/b> 25625."},{"key":"32","doi-asserted-by":"publisher","unstructured":"GRIFFIN, J. E.<\/small>, MATECHOU, E.<\/small>, BUXTON, A. S.<\/small>, BORMPOUDAKIS, D.<\/small> and GRIFFITHS, R. A.<\/small> (2020). Modelling environmental DNA data; Bayesian variable selection accounting for false positive and false negative errors. J. R. Stat. Soc<\/i>., Ser. C, Appl. Stat.<\/i> 69<\/b> 377\u2013392.","DOI":"10.1111\/rssc.12390"},{"key":"40","doi-asserted-by":"crossref","unstructured":"JOSEPH, L.<\/small>, GYORKOS, T. W.<\/small> and COUPAL, L.<\/small> (1995). Bayesian estimation of disease prevalence and the parameters of diagnostic tests in the absence of a gold standard. Amer. J. Epidemiol.<\/i> 141<\/b> 263\u2013272.","DOI":"10.1093\/oxfordjournals.aje.a117428"},{"key":"41","doi-asserted-by":"crossref","unstructured":"JUSTINIANO, A.<\/small> and PRIMICERI, G. E.<\/small> (2008). The time-varying volatility of macroeconomic fluctuations. Amer. Econ. Rev.<\/i> 98<\/b> 604\u2013641.","DOI":"10.1257\/aer.98.3.604"},{"key":"43","doi-asserted-by":"publisher","unstructured":"KANNAN, R.<\/small>, LOV\u00c1SZ, L.<\/small> and SIMONOVITS, M.<\/small> (1997). Random walks and an O<\/mi><\/mrow>\u2217<\/mo><\/mrow><\/msup>(<\/mo>n<\/mi><\/mrow>5<\/mn><\/mrow><\/msup>)<\/mo><\/math> volume algorithm for convex bodies. Random Structures Algorithms<\/i> 11<\/b> 1\u201350.","DOI":"10.1002\/(SICI)1098-2418(199708)11:1<1::AID-RSA1>3.0.CO;2-X"},{"key":"46","doi-asserted-by":"publisher","unstructured":"KLARTAG, B.<\/small> (2023). Logarithmic bounds for isoperimetry and slices of convex sets. Ars Inven. Anal.<\/i> Paper No. 4.","DOI":"10.15781\/jsjy-0b06"},{"key":"47","unstructured":"KOLESNIKOV, A. V.<\/small> (2011). Mass transportation and contractions. arXiv Preprint. Available at arXiv:1103.1479<\/a>."},{"key":"48","doi-asserted-by":"crossref","unstructured":"LEE, H.<\/small> and ZHANG, K.<\/small> (2026). Supplement to \u201cFast mixing of data augmentation algorithms: Bayesian probit, logit and lasso regression.\u201d https:\/\/doi.org\/10.1214\/26-AOS2641SUPPA<\/a>, https:\/\/doi.org\/10.1214\/26-AOS2641SUPPB<\/a>","DOI":"10.1214\/26-AOS2641SUPPB"},{"key":"49","doi-asserted-by":"publisher","unstructured":"LEE, Y. T.<\/small> and VEMPALA, S. S.<\/small> (2017). Eldan\u2019s stochastic localization and the KLS hyperplane conjecture: An improved lower bound for expansion. In 58th Annual IEEE Symposium on Foundations of Computer Science\u2014FOCS<\/i> 2017 998\u20131007. IEEE Computer Soc., Los Alamitos, CA.","DOI":"10.1109\/FOCS.2017.96"},{"key":"54","unstructured":"LOV\u00c1SZ, L.<\/small> and VEMPALA, S.<\/small> (2004). Hit-and-run is fast and fun. Available at https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/tr-2003-05.pdf<\/a>."},{"key":"57","doi-asserted-by":"publisher","unstructured":"MALLICK, H.<\/small> and YI, N.<\/small> (2014). A new Bayesian lasso. Stat. Interface<\/i> 7<\/b> 571\u2013582.","DOI":"10.4310\/SII.2014.v7.n4.a12"},{"key":"59","doi-asserted-by":"publisher","unstructured":"MIKULINCER, D.<\/small> and SHENFELD, Y.<\/small> (2024). The Brownian transport map. Probab. Theory Related Fields<\/i> 190<\/b> 379\u2013444.","DOI":"10.1007\/s00440-024-01286-0"},{"key":"63","doi-asserted-by":"publisher","unstructured":"MONTANARI, A.<\/small> and WU, Y.<\/small> (2026). Provably efficient posterior sampling for sparse linear regression via measure decomposition. J. Amer. Statist. Assoc.<\/i> 121<\/b> 636\u2013654.","DOI":"10.1080\/01621459.2025.2537461"},{"key":"64","unstructured":"MOU, W.<\/small>, HO, N.<\/small>, WAINWRIGHT, M. J.<\/small>, BARTLETT, P. L.<\/small> and JORDAN, M. I.<\/small> (2019). Sampling for Bayesian mixture models: Mcmc with polynomial-time mixing. arXiv Preprint. Available at arXiv:1912.05153<\/a>."},{"key":"65","doi-asserted-by":"publisher","unstructured":"NARAYANAN, H.<\/small> (2016). Randomized interior point methods for sampling and optimization. Ann. Appl. Probab.<\/i> 26<\/b> 597\u2013641.","DOI":"10.1214\/15-AAP1104"},{"key":"66","doi-asserted-by":"crossref","unstructured":"NGUYEN, H. H.<\/small>, NGO, V. M.<\/small> and TRAN, A. N. T.<\/small> (2021). Financial performances, entrepreneurial factors and coping strategy to survive in the COVID-19 pandemic: Case of Vietnam. Res. Int. Bus. Finance<\/i> 56<\/b> 101380.","DOI":"10.1016\/j.ribaf.2021.101380"},{"key":"73","unstructured":"RAJARATNAM, B.<\/small>, SPARKS, D.<\/small>, KHARE, K.<\/small> and ZHANG, L.<\/small> (2015). Scalable Bayesian shrinkage and uncertainty quantification for high-dimensional regression. arXiv preprint. Available at arXiv:1509.03697<\/a>."},{"key":"77","unstructured":"ROY, V.<\/small>, KHARE, K.<\/small> and HOBERT, J. P.<\/small> (2024). The data augmentation algorithm. arXiv preprint. Available at arXiv:2406.10464<\/a>."},{"key":"78","doi-asserted-by":"publisher","unstructured":"SAMPFORD, M. R.<\/small> (1953). Some inequalities on Mill\u2019s ratio and related functions. Ann. Math. Stat.<\/i> 24<\/b> 130\u2013132.","DOI":"10.1214\/aoms\/1177729093"},{"key":"80","doi-asserted-by":"publisher","unstructured":"SINCLAIR, A.<\/small> and JERRUM, M.<\/small> (1989). Approximate counting, uniform generation and rapidly mixing Markov chains. Inform. Comput.<\/i> 82<\/b> 93\u2013133.","DOI":"10.1016\/0890-5401(89)90067-9"},{"key":"81","doi-asserted-by":"publisher","unstructured":"TALAGRAND, M.<\/small> (1991). A new isoperimetric inequality and the concentration of measure phenomenon. In Geometric Aspects of Functional Analysis<\/i> (1989\u2013<\/i>90). Lecture Notes in Math.<\/i> 1469<\/b> 94\u2013124. Springer, Berlin.","DOI":"10.1007\/BFb0089217"},{"key":"85","doi-asserted-by":"publisher","unstructured":"VAN DYK, D. A.<\/small> and MENG, X.-L.<\/small> (2001). The art of data augmentation. J. Comput. Graph. Statist.<\/i> 10<\/b> 1\u2013111.","DOI":"10.1198\/10618600152418584"},{"key":"86","unstructured":"VEMPALA, S.<\/small> and WIBISONO, A.<\/small> (2019). Rapid convergence of the unadjusted Langevin algorithm: Isoperimetry suffices. Adv. Neural Inf. Process. Syst.<\/i> 32<\/b>."},{"key":"88","unstructured":"WIBISONO, A.<\/small> (2019). Proximal Langevin algorithm: Rapid convergence under isoperimetry. arXiv Preprint. Available at arXiv:1911.01469<\/a>."},{"key":"89","unstructured":"XUN, G.<\/small>, LI, Y.<\/small>, ZHAO, W. X.<\/small>, GAO, J.<\/small> and ZHANG, A.<\/small> (2017). A correlated topic model using word embeddings. In IJCAI<\/i> 17<\/b> 4207\u20134213."},{"key":"90","doi-asserted-by":"publisher","unstructured":"ZENS, G.<\/small>, FR\u00dcHWIRTH-SCHNATTER, S.<\/small> and WAGNER, H.<\/small> (2024). Ultimate P\u00f3lya gamma samplers\u2014efficient MCMC for possibly imbalanced binary and categorical data. J. Amer. Statist. Assoc.<\/i> 119<\/b> 2548\u20132559.","DOI":"10.1080\/01621459.2023.2259030"},{"key":"11","doi-asserted-by":"publisher","unstructured":"CAFFARELLI, L. A.<\/small> (2000). Monotonicity properties of optimal transportation and the FKG and related inequalities. Comm. Math. Phys.<\/i> 214<\/b> 547\u2013563.","DOI":"10.1007\/s002200000257"},{"key":"42","doi-asserted-by":"publisher","unstructured":"KANNAN, R.<\/small>, LOV\u00c1SZ, L.<\/small> and SIMONOVITS, M.<\/small> (1995). Isoperimetric problems for convex bodies and a localization lemma. Discrete Comput. Geom.<\/i> 13<\/b> 541\u2013559.","DOI":"10.1007\/BF02574061"},{"key":"60","doi-asserted-by":"publisher","unstructured":"MILMAN, E.<\/small> (2010). Isoperimetric and concentration inequalities: Equivalence under curvature lower bound. Duke Math. J.<\/i> 154<\/b> 207\u2013239.","DOI":"10.1215\/00127094-2010-038"},{"key":"45","doi-asserted-by":"publisher","unstructured":"KIM, Y.-H.<\/small> and MILMAN, E.<\/small> (2012). A generalization of Caffarelli\u2019s contraction theorem via (reverse) heat flow. Math. Ann.<\/i> 354<\/b> 827\u2013862.","DOI":"10.1007\/s00208-011-0749-x"},{"key":"82","doi-asserted-by":"publisher","unstructured":"TALAGRAND, M.<\/small> (1996). Transportation cost for Gaussian and other product measures. Geom. Funct. Anal.<\/i> 6<\/b> 587\u2013600.","DOI":"10.1007\/BF02249265"},{"key":"13","doi-asserted-by":"publisher","unstructured":"CATTIAUX, P.<\/small> and GUILLIN, A.<\/small> (2022). Functional inequalities for perturbed measures with applications to log-concave measures and to some Bayesian problems. Bernoulli<\/i> 28<\/b> 2294\u20132321.","DOI":"10.3150\/21-bej1419"}],"container-title":["The Annals of Statistics"],"original-title":[],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T21:12:26Z","timestamp":1791321146000},"score":1,"resource":{"primary":{"URL":"https:\/\/projecteuclid.org\/journals\/annals-of-statistics\/volume-54\/issue-4\/Fast-mixing-of-data-augmentation-algorithms--Bayesian-probit-logit\/10.1214\/26-AOS2641.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,1]]},"references-count":91,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,8,1]]}},"URL":"https:\/\/doi.org\/10.1214\/26-aos2641","relation":{},"ISSN":["0090-5364","2168-8966"],"issn-type":[{"value":"0090-5364","type":"print"},{"value":"2168-8966","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,1]]}}}