Uncertainty estimation under model misspecification in neural network regression


METADATA ONLY
Loading...

Date

2021-11-23

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

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.

Permanent link

Publication status

published

Editor

Book title

Journal / series

Volume

Pages / Article No.

2111.11763

Publisher

Cornell University

Event

Your Model is Wrong: Robustness and Misspecification in Probabilistic Modeling. Workshop at NeurIPS 2021

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

09479 - Grewe, Benjamin / Grewe, Benjamin check_circle
03672 - Steger, Angelika (emeritus) / Steger, Angelika (emeritus) check_circle

Notes

Poster presentation on December 14, 2021.

Funding

173721 - Temporal Information Integration in Neural Networks (SNF)
189251 - Ultra compact miniaturized microscopes to image meso-scale brain activity (SNF)

Related publications and datasets