Data
Viewed: [[ro.stat.viewed]] Cited: [[ro.stat.cited]] Accessed: [[ro.stat.accessed]]
ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rfr_id=info%3Asid%2FANDS&rft_id=info:doi10.26180/25302625.v1&rft.title=Loss-Based Variational Bayes Prediction&rft.identifier=https://doi.org/10.26180/25302625.v1&rft.publisher=Monash University&rft.description=We propose a new approach to 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 generalized 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.&rft.creator=Bonsoo Koo&rft.creator=David Frazier&rft.creator=Gael M. Martin&rft.creator=Ruben Loaiza Maya&rft.date=2024&rft_rights=CC-BY-4.0&rft_subject=Variational Bayesian approach&rft.type=dataset&rft.language=English Access the data

Licence & Rights:

Open Licence view details
CC-BY

CC-BY-4.0

Full description

We propose a new approach to 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 generalized 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.

Issued: 2024-02-28

Created: 2024-02-28

This dataset is part of a larger collection

Click to explore relationships graph
Subjects

User Contributed Tags    

Login to tag this record with meaningful keywords to make it easier to discover

Identifiers
ACN 633 798 857