Correcting Predictions for Approximate Bayesian Inference


  • Tomasz Kuśmierczyk University of Helsinki
  • Joseph Sakaya University of Helsinki
  • Arto Klami University of Helsinki



Bayesian models quantify uncertainty and facilitate optimal decision-making in downstream applications. For most models, however, practitioners are forced to use approximate inference techniques that lead to sub-optimal decisions due to incorrect posterior predictive distributions. We present a novel approach that corrects for inaccuracies in posterior inference by altering the decision-making process. We train a separate model to make optimal decisions under the approximate posterior, combining interpretable Bayesian modeling with optimization of direct predictive accuracy in a principled fashion. The solution is generally applicable as a plug-in module for predictive decision-making for arbitrary probabilistic programs, irrespective of the posterior inference strategy. We demonstrate the approach empirically in several problems, confirming its potential.




How to Cite

Kuśmierczyk, T., Sakaya, J., & Klami, A. (2020). Correcting Predictions for Approximate Bayesian Inference. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 4511-4518.



AAAI Technical Track: Machine Learning