DeepAI AI Chat
Log In Sign Up

Uncertainty estimation under model misspecification in neural network regression

by   Maria R. Cervera, et al.

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.


page 2

page 3


Optimal designs for frequentist model averaging

We consider the problem of designing experiments for the estimation of a...

Quantifying Aleatoric and Epistemic Uncertainty Using Density Estimation in Latent Space

The distribution of a neural network's latent representations has been s...

Improving Regression Uncertainty Estimates with an Empirical Prior

While machine learning models capable of producing uncertainty estimates...

Empirical Likelihood Estimation for Linear Regression Models with AR(p) Error Terms

Linear regression models are useful statistical tools to analyze data se...

Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression

We propose a new model that estimates uncertainty in a single forward pa...

Faithful Heteroscedastic Regression with Neural Networks

Heteroscedastic regression models a Gaussian variable's mean and varianc...

Modelling heterogeneous distributions with an Uncountable Mixture of Asymmetric Laplacians

In regression tasks, aleatoric uncertainty is commonly addressed by cons...