Show simple item record

dc.contributor.authorVenturi, Daniele
dc.contributor.authorPerdikaris, Paris
dc.contributor.authorKarniadakis, George E
dc.date.accessioned2017-05-24T18:50:06Z
dc.date.available2017-05-24T18:50:06Z
dc.date.issued2016-07
dc.date.submitted2016-01
dc.identifier.issn1064-8275
dc.identifier.issn1095-7197
dc.identifier.urihttp://hdl.handle.net/1721.1/109316
dc.description.abstractWe develop a framework for multifidelity information fusion and predictive inference in high-dimensional input spaces and in the presence of massive data sets. Hence, we tackle simultaneously the “big N" problem for big data and the curse of dimensionality in multivariate parametric problems. The proposed methodology establishes a new paradigm for constructing response surfaces of high-dimensional stochastic dynamical systems, simultaneously accounting for multifidelity in physical models as well as multifidelity in probability space. Scaling to high dimensions is achieved by data-driven dimensionality reduction techniques based on hierarchical functional decompositions and a graph-theoretic approach for encoding custom autocorrelation structure in Gaussian process priors. Multifidelity information fusion is facilitated through stochastic autoregressive schemes and frequency-domain machine learning algorithms that scale linearly with the data. Taking together these new developments leads to linear complexity algorithms as demonstrated in benchmark problems involving deterministic and stochastic fields in up to 10⁵ input dimensions and 10⁵ training points on a standard desktop computer.en_US
dc.language.isoen_US
dc.publisherSociety for Industrial and Applied Mathematicsen_US
dc.relation.isversionofhttp://dx.doi.org/10.1137/15M1055164en_US
dc.rightsArticle is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.en_US
dc.sourceSIAMen_US
dc.titleMultifidelity Information Fusion Algorithms for High-Dimensional Systems and Massive Data setsen_US
dc.typeArticleen_US
dc.identifier.citationPerdikaris, Paris; Venturi, Daniele and Karniadakis, George Em. “Multifidelity Information Fusion Algorithms for High-Dimensional Systems and Massive Data Sets.” SIAM Journal on Scientific Computing 38, no. 4 (January 2016): B521–B538 © 2016 Society for Industrial and Applied Mathematicsen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Mechanical Engineeringen_US
dc.contributor.mitauthorPerdikaris, Paris
dc.contributor.mitauthorKarniadakis, George E
dc.relation.journalSIAM Journal on Scientific Computingen_US
dc.eprint.versionFinal published versionen_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/PeerRevieweden_US
dspace.orderedauthorsPerdikaris, Paris; Venturi, Daniele; Karniadakis, George Emen_US
dspace.embargo.termsNen_US
dc.identifier.orcidhttps://orcid.org/0000-0001-8042-8354
mit.licensePUBLISHER_POLICYen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record