{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:04:40Z","timestamp":1760144680158,"version":"build-2065373602"},"reference-count":40,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T00:00:00Z","timestamp":1715731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NSF DMS","award":["2210689"],"award-info":[{"award-number":["2210689"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>We consider the estimation of the marginal likelihood in Bayesian statistics, with primary emphasis on Gaussian graphical models, where the intractability of the marginal likelihood in high dimensions is a frequently researched problem. We propose a general algorithm that can be widely applied to a variety of problem settings and excels particularly when dealing with near log-concave posteriors. Our method builds upon a previously posited algorithm that uses MCMC samples to partition the parameter space and forms piecewise constant approximations over these partition sets as a means of estimating the normalizing constant. In this paper, we refine the aforementioned local approximations by taking advantage of the shape of the target distribution and leveraging an expectation propagation algorithm to approximate Gaussian integrals over rectangular polytopes. Our numerical experiments show the versatility and accuracy of the proposed estimator, even as the parameter space increases in dimension and becomes more complicated.<\/jats:p>","DOI":"10.3390\/a17050213","type":"journal-article","created":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T06:14:42Z","timestamp":1715753682000},"page":"213","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EPSOM-Hyb: A General Purpose Estimator of Log-Marginal Likelihoods with Applications in Probabilistic Graphical Models"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1009-4314","authenticated-orcid":false,"given":"Eric","family":"Chuu","sequence":"first","affiliation":[{"name":"Department of Statistics, Texas A&M University, 3143 TAMU, College Station, TX 77843, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8087-6747","authenticated-orcid":false,"given":"Yabo","family":"Niu","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of Houston, 4800 Calhoun Rd., Houston, TX 77004, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anirban","family":"Bhattacharya","sequence":"additional","affiliation":[{"name":"Department of Statistics, Texas A&M University, 3143 TAMU, College Station, TX 77843, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Debdeep","family":"Pati","sequence":"additional","affiliation":[{"name":"Department of Statistics, Texas A&M University, 3143 TAMU, College Station, TX 77843, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,5,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Lauritzen, S.L. (1996). Graphical Models, Clarendon Press.","DOI":"10.1093\/oso\/9780198522195.001.0001"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Maathuis, M., Drton, M., Lauritzen, S., and Wainwright, M. (2018). Handbook of Graphical Models, CRC Press, Inc.. [1st ed.].","DOI":"10.1201\/9780429463976"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1080\/01621459.1986.10478240","article-title":"Accurate Approximations for Posterior Moments and Marginal Densities","volume":"81","author":"Tierney","year":"1986","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1111\/j.2517-6161.1994.tb01956.x","article-title":"Approximate Bayesian Inference with the Weighted Likelihood Bootstrap","volume":"56","author":"Newton","year":"1994","journal-title":"J. R. Stat. Soc. Ser. B"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1198\/jcgs.2009.08022","article-title":"Simulation Pseudo-Bias Correction to the Harmonic Mean Estimator of Integrated Likelihoods","volume":"18","author":"Lenk","year":"2009","journal-title":"J. Comput. Graph. Stat."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1214\/16-BA1001","article-title":"Estimating the Marginal Likelihood Using the Arithmetic Mean Identity","volume":"12","author":"Pajor","year":"2017","journal-title":"Bayesian Anal."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1023\/A:1008923215028","article-title":"Annealed importance sampling","volume":"11","author":"Neal","year":"2001","journal-title":"Stat. Comput."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1313","DOI":"10.1080\/01621459.1995.10476635","article-title":"Marginal Likelihood from the Gibbs Output","volume":"90","author":"Chib","year":"1995","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_9","first-page":"831","article-title":"Simulating ratios of normalizing constants via a simple identity: A theoretical exploration","volume":"6","author":"Meng","year":"1996","journal-title":"Stat. Sin."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1198\/106186002457","article-title":"Warp Bridge Sampling","volume":"11","author":"Meng","year":"2002","journal-title":"J. Comput. Graph. Stat."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1214\/06-BA127","article-title":"Nested sampling for general Bayesian computation","volume":"1","author":"Skilling","year":"2006","journal-title":"Bayesian Anal."},{"key":"ref_12","unstructured":"Hubin, A., and Storvik, G. (2016). Estimating the marginal likelihood with Integrated nested Laplace approximation (INLA). arXiv."},{"key":"ref_13","unstructured":"Barthelm\u00e9, S., and Chopin, N. (2011). Expectation-Propagation for Likelihood-Free Inference. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1093\/biomet\/87.1.99","article-title":"Cholesky decomposition of a hyper inverse Wishart matrix","volume":"87","author":"Roverato","year":"2000","journal-title":"Biometrika"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1093\/biomet\/86.4.785","article-title":"Decomposable graphical Gaussian model determination","volume":"86","author":"Giudici","year":"1999","journal-title":"Biometrika"},{"key":"ref_16","first-page":"43","article-title":"Bayesian inference for nondecomposable graphical Gaussian models","volume":"65","author":"Dellaportas","year":"2003","journal-title":"Sankhy\u0101 Indian J. Stat."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1093\/biomet\/92.2.317","article-title":"A Monte Carlo method for computing the marginal likelihood in nondecomposable Gaussian graphical models","volume":"92","author":"Massam","year":"2005","journal-title":"Biometrika"},{"key":"ref_18","unstructured":"Khare, K., Rajaratnam, B., and Saha, A. (2015). Bayesian inference for Gaussian graphical models beyond decomposable graphs. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1111\/1467-9469.00182","article-title":"Independence Structure of Natural Conjugate Densities to Exponential Families and the Gibbs\u2019 Sampler","volume":"27","author":"Piccioni","year":"2000","journal-title":"Scand. J. Stat."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2818","DOI":"10.1214\/08-AOS619","article-title":"Flexible covariance estimation in graphical Gaussian models","volume":"36","author":"Rajaratnam","year":"2008","journal-title":"Ann. Stat."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1002\/sta4.23","article-title":"A Direct Sampler for G-Wishart Variates","volume":"2","author":"Lenkoski","year":"2013","journal-title":"Stat"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1214\/17-AOS1543","article-title":"Exact Formulas for the Normalizing Constants of Wishart Distributions for Graphical Models","volume":"46","author":"Uhler","year":"2018","journal-title":"Ann. Stat."},{"key":"ref_23","unstructured":"Bhadra, A., Sagar, K., Banerjee, S., and Datta, J. (2022). Graphical Evidence. arXiv."},{"key":"ref_24","unstructured":"Chuu, E., Pati, D., and Bhattacharya, A. (2021, January 13\u201315). A Hybrid Approximation to the Marginal Likelihood. Proceedings of the AISTATS, San Diego, CA, USA."},{"key":"ref_25","unstructured":"Breiman, L. (1984). Classification and Regression Trees, Wadsworth International Group."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"837","DOI":"10.1214\/009053606000000029","article-title":"Misspecification in infinite-dimensional Bayesian statistics","volume":"34","author":"Kleijn","year":"2006","journal-title":"Ann. Statist."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1214\/009053606000001172","article-title":"Convergence rates of posterior distributions for noniid observations","volume":"35","author":"Ghosal","year":"2007","journal-title":"Ann. Stat."},{"key":"ref_28","unstructured":"Vaart, A.W.v.d. (1998). Asymptotic Statistics, Cambridge University Press. Cambridge Series in Statistical and Probabilistic Mathematics."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1080\/10618600.1992.10477010","article-title":"Numerical Computation of Multivariate Normal Probabilities","volume":"1","author":"Genz","year":"1992","journal-title":"J. Comput. Graph. Stat."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1111\/rssb.12162","article-title":"The normal law under linear restrictions: Simulation and estimation via minimax tilting","volume":"79","author":"Botev","year":"2016","journal-title":"J. R. Stat. Soc. Ser. B"},{"key":"ref_31","unstructured":"Minka, T.P. (2013). Expectation Propagation for approximate Bayesian inference. arXiv."},{"key":"ref_32","unstructured":"Cunningham, J.P., Hennig, P., and Lacoste-Julien, S. (2011). Gaussian probabilities and expectation propagation. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v089.i03","article-title":"BDgraph: An R Package for Bayesian Structure Learning in Graphical Models","volume":"89","author":"Mohammadi","year":"2019","journal-title":"J. Stat. Softw."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1214\/aos\/1176344611","article-title":"Conjugate priors for exponential families","volume":"7","author":"Diaconis","year":"1979","journal-title":"Ann. Stat."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1272","DOI":"10.1214\/aos\/1176349260","article-title":"Hyper Markov laws in the statistical analysis of decomposable graphical models","volume":"21","author":"Dawid","year":"1993","journal-title":"Ann. Statist."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1016\/0196-6774(86)90023-4","article-title":"Graph minors. II. Algorithmic aspects of tree-width","volume":"7","author":"Robertson","year":"1986","journal-title":"J. Algorithms"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1214\/14-BA874","article-title":"The Performance of Covariance Selection Methods That Consider Decomposable Models Only","volume":"9","author":"Fitch","year":"2014","journal-title":"Bayesian Anal."},{"key":"ref_38","unstructured":"Chuu, E. (2024, May 10). hybrid: Hybrid Approximation to the Marginal Likelihood, R package version 1.0.; 2022. Available online: https:\/\/proceedings.mlr.press\/v130\/chuu21a.html."},{"key":"ref_39","unstructured":"Chuu, E. (R package, 2022). graphml: Hybrid Approximation for Computing Normalizing Constants of G-Wishart Densities, R package, version 1.0."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1214\/088342305000000304","article-title":"Experiments in Stochastic Computation for High-Dimensional Graphical Models","volume":"20","author":"Jones","year":"2005","journal-title":"Stat. Sci."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/5\/213\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:42:38Z","timestamp":1760107358000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/5\/213"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,15]]},"references-count":40,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,5]]}},"alternative-id":["a17050213"],"URL":"https:\/\/doi.org\/10.3390\/a17050213","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2024,5,15]]}}}