{"doi":"10.1137/16m1084080","title":"Parallel Local Approximation MCMC for Expensive Models","abstract":null,"journal":"SIAM/ASA Journal on Uncertainty Quantification","year":2018,"id":596864,"datarank":0.5375278407684165,"base_score":3.58351893845611,"endowment":3.58351893845611,"self_citation_contribution":0.5375278407684165,"citation_network_contribution":0.0,"self_endowment_contribution":0.5375278407684165,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":35,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":402076,"name":"Andrew D. Davis","orcid":"0000-0002-6078-0163","position":1,"is_corresponding":false},{"id":1528791,"name":"Youssef M. Marzouk","orcid":null,"position":2,"is_corresponding":false},{"id":526219,"name":"Natesh S. Pillai","orcid":null,"position":3,"is_corresponding":false},{"id":1460682,"name":"Aaron Smith","orcid":"0000-0001-6796-5155","position":4,"is_corresponding":false},{"id":1528790,"name":"Patrick R. Conrad","orcid":null,"position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Parallel Local Approximation MCMC for Expensive Models","abstract":"Performing Bayesian inference via Markov chain Monte Carlo (MCMC) can be exceedingly expensive when posterior evaluations invoke the evaluation of a computationally expensive model, such as a system of PDEs. In recent work [J. Amer. Statist. Assoc., 111 (2016), pp. 1591--1607] we described a framework for constructing and refining local approximations of such models during an MCMC simulation. These posterior-adapted approximations harness regularity of the model to reduce the computational cost of inference while preserving asymptotic exactness of the Markov chain. Here we describe two extensions of that work. First, we prove that samplers running in parallel can collaboratively construct a shared posterior approximation while ensuring ergodicity of each associated chain, providing a novel opportunity for exploiting parallel computation in MCMC. Second, focusing on the Metropolis-adjusted Langevin algorithm, we describe how a proposal distribution can successfully employ gradients and other relevant information extracted from the approximation. We investigate the practical performance of our approach using two challenging inference problems, the first in subsurface hydrology and the second in glaciology. Using local approximations constructed via parallel chains, we successfully reduce the run time needed to characterize the posterior distributions in these problems from days to hours and from months to days, respectively, dramatically improving the tractability of Bayesian inference.","is_dataset_classified":null,"base_score":0.0,"endowment":0.0,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"23304386","pmcid":null,"openalex_id":"https://openalex.org/W2505308168","authors":[],"funders":[{"funder_name":"Office of Science","grant_id":"DE-SC0007099","title":null},{"funder_name":"Natural Sciences and Engineering Research Council of Canada","grant_id":"unidentified","title":"unidentified"}],"total_grants":2,"fwci":0.0,"citation_percentile":0.00689091,"influential_citations":0,"citation_trend":[],"oa_status":"green","license":"arXiv Non-Exclusive Distribution","oa_locations":[{"url":"https://arxiv.org/pdf/1607.02788","host_type":"repository"},{"url":"https://arxiv.org/pdf/1607.02788","host_type":"repository"},{"url":"https://epubs.siam.org/doi/pdf/10.1137/16M1084080","host_type":"publisher"},{"url":"http://arxiv.org/abs/1607.02788","host_type":"repository"},{"url":"https://doi.org/10.1137/16m1084080","host_type":"journal"},{"url":"https://arxiv.org/abs/1607.02788","host_type":"repository"},{"url":"http://hdl.handle.net/1721.1/120851","host_type":"repository"},{"url":"https://doi.org/10.48550/arxiv.1607.02788","host_type":"repository"},{"url":"http://arxiv.org/pdf/1607.02788","host_type":""},{"url":"https://dx.doi.org/10.48550/arxiv.1607.02788","host_type":""},{"url":"https://zbmath.org/6861803","host_type":""},{"url":"https://doi.org/10.1137/16M1084080","host_type":""},{"url":"https://dx.doi.org/10.1137/16m1084080","host_type":""},{"url":"https://hdl.handle.net/1721.1/120851","host_type":""},{"url":"https://doi.org/https://doi.org/10.1137/16M1084080","host_type":""}],"fields_of_study":["Markov Chains and Monte Carlo Methods","Gaussian Processes and Bayesian Inference","Bayesian Methods and Mixture Models","01 natural sciences","0101 mathematics"],"mesh_terms":[],"keywords":["Markov chain Monte Carlo","Computer science","Inference","Bayesian inference","Posterior probability","Approximate Bayesian computation","Bayesian probability","Markov chain","Algorithm","Approximate inference","Computation","Mathematical optimization","Ergodicity","Applied mathematics","Mathematics","Machine learning","Artificial intelligence","Statistics","FOS: Computer and information sciences","parallel computing","Monte Carlo methods","Statistics - Computation","Statistics - Applications","surrogate modeling","Methodology (stat.ME)","65C40, 62F15, 60J22","local regression","Computational methods in Markov chains","Numerical analysis or methods applied to Markov chains","Metropolis-adjusted Langevin algorithm","Applications (stat.AP)","approximation theory","Statistics - Methodology","Computation (stat.CO)"],"sdg_mappings":[],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-07-28T11:33:17.296405Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}