# Correcting Predictions for Approximate Bayesian Inference

arXiv: https://arxiv.org/abs/1909.04919 · HTML: https://mlsanity.com/paper/1909.04919/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2019.

## Built on by (most cited first, 4 of 4)

- [Post-hoc loss-calibration for Bayesian neural networks](https://mlsanity.com/paper/2106.06997/) (2021)
- [Loss-calibrated expectation propagation for approximate Bayesian decision-making](https://mlsanity.com/paper/2201.03128/) (2022)
- [Amortized Bayesian Decision Making for simulation-based models](https://mlsanity.com/paper/2312.02674/) (2023)
- [Understanding and mitigating difficulties in posterior predictive evaluation](https://mlsanity.com/paper/2405.19747/) (2024)

## Abstract (arXiv)

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.