Uncertainty estimation under model misspecification in neural network regression
arXiv:2111.11763
Abstract
Although neural networks are powerful function approximators, the underlying modelling assumptions ultimately define the likelihood and thus the hypothesis class they are parameterizing. In classification, these assumptions are minimal as the commonly employed softmax is capable of representing any categorical distribution. In regression, however, restrictive assumptions on the type of continuous distribution to be realized are typically placed, like the dominant choice of training via mean-squared error and its underlying Gaussianity assumption. Recently, modelling advances allow to be agnostic to the type of continuous distribution to be modelled, granting regression the flexibility of classification models. While past studies stress the benefit of such flexible regression models in terms of performance, here we study the effect of the model choice on uncertainty estimation. We highlight that under model misspecification, aleatoric uncertainty is not properly captured, and that a Bayesian treatment of a misspecified model leads to unreliable epistemic uncertainty estimates. Overall, our study provides an overview on how modelling choices in regression may influence uncertainty estimation and thus any downstream decision making process.
arXiv commentPublished at the NeurIPS 2021 workshop "Your Model Is Wrong: Robustness and Misspecification in Probabilistic Modeling"
References in corpus (9)
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
- On Calibration of Modern Neural Networks
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
- Normalizing Flows for Probabilistic Modeling and Inference
- Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
- Conditional Density Estimation with Bayesian Normalising Flows
- On Posterior Concentration in Misspecified Models
- Are Bayesian neural networks intrinsically good at out-of-distribution detection?