Deep Anti-Regularized Ensembles provide reliable out-of-distribution uncertainty quantification

by   Antoine de Mathelin, et al.

We consider the problem of uncertainty quantification in high dimensional regression and classification for which deep ensemble have proven to be promising methods. Recent observations have shown that deep ensemble often return overconfident estimates outside the training domain, which is a major limitation because shifted distributions are often encountered in real-life scenarios. The principal challenge for this problem is to solve the trade-off between increasing the diversity of the ensemble outputs and making accurate in-distribution predictions. In this work, we show that an ensemble of networks with large weights fitting the training data are likely to meet these two objectives. We derive a simple and practical approach to produce such ensembles, based on an original anti-regularization term penalizing small weights and a control process of the weight increase which maintains the in-distribution loss under an acceptable threshold. The developed approach does not require any out-of-distribution training data neither any trade-off hyper-parameter calibration. We derive a theoretical framework for this approach and show that the proposed optimization can be seen as a "water-filling" problem. Several experiments in both regression and classification settings highlight that Deep Anti-Regularized Ensembles (DARE) significantly improve uncertainty quantification outside the training domain in comparison to recent deep ensembles and out-of-distribution detection methods. All the conducted experiments are reproducible and the source code is available at <>.


page 11

page 24


Towards Reliable Uncertainty Quantification via Deep Ensembles in Multi-output Regression Task

Deep ensemble is a simple and straightforward approach for approximating...

Multi-Head Multi-Loss Model Calibration

Delivering meaningful uncertainty estimates is essential for a successfu...

A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness

Accurate uncertainty quantification is a major challenge in deep learnin...

Greedy Bayesian Posterior Approximation with Deep Ensembles

Ensembles of independently trained neural networks are a state-of-the-ar...

REDS: Random Ensemble Deep Spatial prediction

There has been a great deal of recent interest in the development of spa...

Why have a Unified Predictive Uncertainty? Disentangling it using Deep Split Ensembles

Understanding and quantifying uncertainty in black box Neural Networks (...

Multi-Symmetry Ensembles: Improving Diversity and Generalization via Opposing Symmetries

Deep ensembles (DE) have been successful in improving model performance ...

Please sign up or login with your details

Forgot password? Click here to reset