Loss-Based Variational Bayes Prediction

David Frazier (), Ruben Loaiza-Maya (), Gael Martin () and Bonsoo Koo Bonsoo Koo ()
Authors registered in the RePEc Author Service: Rubén Albeiro Loaiza Maya

No 8/21, Monash Econometrics and Business Statistics Working Papers from Monash University, Department of Econometrics and Business Statistics

Abstract: We propose a new method for Bayesian prediction that caters for models with a large number of parameters and is robust to model misspecification. Given a class of high-dimensional (but parametric) predictive models, this new approach constructs a posterior predictive using a variational approximation to a loss-based, or Gibbs, posterior that is directly focused on predictive accuracy. The theoretical behavior of the new prediction approach is analyzed and a form of optimality demonstrated. Applications to both simulated and empirical data using high-dimensional Bayesian neural network and autoregressive mixture models demonstrate that the approach provides more accurate results than various alternatives, including misspecified likelihood-based predictions.

Keywords: loss-based Bayesian forecasting; variational inference; Gibbs posteriors; proper scoring rules; Bayesian neural networks; M4 forecasting competition (search for similar items in EconPapers)
JEL-codes: C11 C53 C58 (search for similar items in EconPapers)
Pages: 44
Date: 2021
New Economics Papers: this item is included in nep-big, nep-cmp, nep-for, nep-isf and nep-ore
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
https://www.monash.edu/business/ebs/research/publications/ebs/wp08-2021.pdf (application/pdf)

Related works:
Working Paper: Loss-Based Variational Bayes Prediction (2022)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:msh:ebswps:2021-8

Ordering information: This working paper can be ordered from
http://business.mona ... -business-statistics

Access Statistics for this paper

More papers in Monash Econometrics and Business Statistics Working Papers from Monash University, Department of Econometrics and Business Statistics PO Box 11E, Monash University, Victoria 3800, Australia. Contact information at EDIRC.
Bibliographic data for series maintained by Professor Xibin Zhang ().