Projekteja vuodessa
Abstrakti
This paper focusses on the formulation of numerical integration as an inferential task. To date, research effort has largely focussed on the development of Bayesian cubature, whose distributional output provides uncertainty quantification for the integral. However, the point estimators associated to Bayesian cubature can be inaccurate and acutely sensitive to the prior when the domain is high-dimensional. To address these drawbacks we introduce Bayes–Sard cubature, a probabilistic framework that combines the flexibility of Bayesian cubature with the robustness of classical cubatures which are well-established. This is achieved by considering a Gaussian process model for the integrand whose mean is a parametric regression model, with an improper prior on each regression coefficient. The features in the regression model consist of test functions which are guaranteed to be exactly integrated, with remaining degrees of freedom afforded to the non-parametric part. The asymptotic convergence of the Bayes–Sard cubature method is established and the theoretical results are numerically verified. In particular, we report two orders of magnitude reduction in error compared to Bayesian cubature in the context of a high-dimensional financial integral.
Alkuperäiskieli | Englanti |
---|---|
Otsikko | Advances in Neural Information Processing Systems 31 |
Alaotsikko | Proceedings of NIPS2017 |
Kustantaja | Curran Associates Inc. |
Sivumäärä | 12 |
Tila | Julkaistu - jouluk. 2018 |
OKM-julkaisutyyppi | A4 Artikkeli konferenssijulkaisussa |
Tapahtuma | Conference on Neural Information Processing Systems - Palais des Congrès de Montréal, Montréal, Kanada Kesto: 2 jouluk. 2018 → 8 jouluk. 2018 Konferenssinumero: 32 http://nips.cc |
Julkaisusarja
Nimi | Advances in neural information processing systems |
---|---|
Kustantaja | Curran Associates |
Numero | 31 |
ISSN (painettu) | 1049-5258 |
Conference
Conference | Conference on Neural Information Processing Systems |
---|---|
Lyhennettä | NeurIPS |
Maa/Alue | Kanada |
Kaupunki | Montréal |
Ajanjakso | 02/12/2018 → 08/12/2018 |
www-osoite |
Sormenjälki
Sukella tutkimusaiheisiin 'A Bayes–Sard Cubature Method'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.Projektit
- 2 Päättynyt
-
Probabilistinen syväoppiminen hierarkkisilla stokastisilla osittaisdifferentiaaliyhtälöillä
Särkkä, S., Karvonen, T., Sarmavuori, J., Raitoharju, M., Bahrami Rad, A., Hostettler, R., Emzir, M., Gao, R., Purisha, Z. & Tronarp, F.
01/01/2018 → 31/12/2019
Projekti: Academy of Finland: Other research funding
-
Sekventiaalisia Monte Carlo -menetelmiä tila- ja parametriestimointiin stokastisissa dynaamisissa systeemeissä
Särkkä, S., Bahrami Rad, A., Hostettler, R., Sarmavuori, J., Suotsalo, K., Karvonen, T., Garcia Fernandez, A. & Raitoharju, M.
01/09/2016 → 31/08/2018
Projekti: Academy of Finland: Other research funding