Title: Loss-based variational Bayes prediction
Authors: Gael Martin - Monash University (Australia) [presenting]
Abstract: A new method is proposed 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 behaviour of the new prediction approach is analyzed, and a form of optimality demonstrated. Applications to Bayesian neural network models, autoregressive mixture models, and to the M4 forecasting competition, demonstrate that the approach provides more accurate results than various alternatives, including misspecified likelihood-based predictions.