dc.contributor.author | Lykkegaard, MB | |
dc.contributor.author | Mingas, G | |
dc.contributor.author | Scheichl, R | |
dc.contributor.author | Fox, C | |
dc.contributor.author | Dodwell, TJ | |
dc.date.accessioned | 2021-05-17T12:48:41Z | |
dc.date.issued | 2020-12-12 | |
dc.description.abstract | Uncertainty Quantification through Markov Chain Monte Carlo (MCMC) can be prohibitively expensive for target probability densities with expensive likelihood functions, for instance when the evaluation it involves solving a Partial Differential Equation (PDE), as is the case in a wide range of engineering applications. Multilevel Delayed Acceptance (MLDA) with an Adaptive Error Model (AEM) is a novel approach, which alleviates this problem by exploiting a hierarchy of models, with increasing complexity and cost, and correcting the inexpensive models on-the-fly. The method has been integrated within the open-source probabilistic programming package PyMC3 and is available in the latest development version. In this paper, the algorithm is presented along with an illustrative example. | en_GB |
dc.description.sponsorship | Turing AI fellowship | en_GB |
dc.description.sponsorship | Engineering and Physical Sciences Research Council (EPSRC) | en_GB |
dc.identifier.citation | In: Machine Learning for Engineering Modeling, Simulation, and Design Workshop at Neural Information Processing Systems 2020 (NeurIPS 2020), 6 - 12 December 2020. Poster 4. Virtual. | en_GB |
dc.identifier.grantnumber | 2TAFFP\100007 | en_GB |
dc.identifier.grantnumber | EP/L016214/1 | en_GB |
dc.identifier.uri | http://hdl.handle.net/10871/125705 | |
dc.language.iso | en | en_GB |
dc.publisher | NeurIPS 2020 | en_GB |
dc.relation.url | https://ml4eng.github.io/ | en_GB |
dc.rights | © 2020 NeurIPS 2020 | en_GB |
dc.title | Multilevel Delayed Acceptance MCMC with an Adaptive Error Model in PyMC3 | en_GB |
dc.type | Conference paper | en_GB |
dc.date.available | 2021-05-17T12:48:41Z | |
dc.description | This is the final version. Available from NeurIPS 2020 via the DOI in this record | en_GB |
dc.rights.uri | http://www.rioxx.net/licenses/all-rights-reserved | en_GB |
dcterms.dateAccepted | 2020-09-26 | |
rioxxterms.version | VoR | en_GB |
rioxxterms.licenseref.startdate | 2020-12-12 | |
rioxxterms.type | Conference Paper/Proceeding/Abstract | en_GB |
refterms.dateFCD | 2021-05-17T12:44:31Z | |
refterms.versionFCD | VoR | |
refterms.dateFOA | 2021-05-17T12:48:49Z | |
refterms.panel | B | en_GB |