Conference Papers Year : 2024

Combining Statistical Depth and Fermat Distance for Uncertainty Quantification

Abstract

We measure the out-of-domain uncertainty in the prediction of Neural Networks using a statistical notion called "Lens Depth" (LD) combined with Fermat Distance, which is able to capture precisely the "depth" of a point with respect to a distribution in feature space, without any distributional assumption. Our method also has no trainable parameter. The method is applied directly in the feature space at test time and does not intervene in training process. As such, it does not impact the performance of the original model. The proposed method gives excellent qualitative results on toy datasets and can give competitive or better uncertainty estimation on standard deep learning datasets compared to strong baseline methods.
Fichier principal
Vignette du fichier
LD_Fermat_neurips_20_12.pdf (7) Télécharger le fichier
Origin Files produced by the author(s)
Licence

Dates and versions

hal-04851165 , version 1 (20-12-2024)

Licence

Identifiers

  • HAL Id : hal-04851165 , version 1

Cite

Hai-Vy Nguyen, Fabrice Gamboa, Reda Chhaibi, Sixin Zhang, Serge Gratton, et al.. Combining Statistical Depth and Fermat Distance for Uncertainty Quantification. The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024), Dec 2024, Vancouver, Canada. ⟨hal-04851165⟩
51 View
15 Download

Share

More