dc.contributor.author | Marzouk, Youssef M | |
dc.contributor.author | Spantini, Alessio | |
dc.date.accessioned | 2020-08-12T13:31:17Z | |
dc.date.available | 2020-08-12T13:31:17Z | |
dc.date.issued | 2018-12 | |
dc.identifier.uri | https://hdl.handle.net/1721.1/126535 | |
dc.description.abstract | Stein variational gradient descent (SVGD) was recently proposed as a general purpose nonparametric variational inference algorithm [Liu & Wang, NIPS 2016]: it minimizes the Kullback-Leibler divergence between the target distribution and its approximation by implementing a form of functional gradient descent on a reproducing kernel Hilbert space. In this paper, we accelerate and generalize the SVGD algorithm by including second-order information, thereby approximating a Newton-like iteration in function space. We also show how second-order information can lead to more effective choices of kernel. We observe significant computational gains over the original SVGD algorithm in multiple test cases. | en_US |
dc.language.iso | en | |
dc.publisher | Curran Associates, Inc. | en_US |
dc.relation.isversionof | https://papers.nips.cc/paper/8130-a-stein-variational-newton-method | en_US |
dc.rights | Article 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.source | Neural Information Processing Systems (NIPS) | en_US |
dc.title | A Stein variational Newton method | en_US |
dc.type | Article | en_US |
dc.identifier.citation | Detommaso, Gianluca et al. “A Stein variational Newton method.” Paper presented at the 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, Canada, 3-8 December 2018, Curran Associates, Inc. © 2018 The Author(s) | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics | en_US |
dc.relation.journal | 32nd Conference on Neural Information Processing Systems (NeurIPS 2018) | en_US |
dc.eprint.version | Final published version | en_US |
dc.type.uri | http://purl.org/eprint/type/ConferencePaper | en_US |
eprint.status | http://purl.org/eprint/status/NonPeerReviewed | en_US |
dc.date.updated | 2019-10-29T18:06:06Z | |
dspace.date.submission | 2019-10-29T18:06:09Z | |
mit.journal.volume | 2018 | en_US |
mit.metadata.status | Complete | |