AutoDEUQ: Automated Deep Ensemble with Uncertainty Quantification - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

AutoDEUQ: Automated Deep Ensemble with Uncertainty Quantification

Abstract

Deep neural networks are powerful predictors for a variety of tasks. However, they do not capture uncertainty directly. Using neural network ensembles to quantify uncertainty is competitive with approaches based on Bayesian neural networks while benefiting from better computational scalability. However, building ensembles of neural networks is a challenging task because, in addition to choosing the right neural architecture or hyperparameters for each member of the ensemble, there is an added cost of training each model. We propose AutoDEUQ, an automated approach for generating an ensemble of deep neural networks. Our approach leverages joint neural architecture and hyperparameter search to generate ensembles. We use the law of total variance to decompose the predictive variance of deep ensembles into aleatoric (data) and epistemic (model) uncertainties. We show that AutoDEUQ outperforms probabilistic backpropagation, Monte Carlo dropout, deep ensemble, distribution-free ensembles, and hyper ensemble methods on a number of regression benchmarks.
Fichier principal
Vignette du fichier
AAAI_Uncertainty.pdf (614.17 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03518597 , version 1 (10-01-2022)

Identifiers

  • HAL Id : hal-03518597 , version 1

Cite

Romain Egele, Romit Maulik, Krishnan Raghavan, Bethany Lusch, Isabelle Guyon, et al.. AutoDEUQ: Automated Deep Ensemble with Uncertainty Quantification. 26TH International Conference on Pattern Recognition, Aug 2022, Montréal, Canada. pp.1908-1914. ⟨hal-03518597⟩
130 View
449 Download

Share

Gmail Mastodon Facebook X LinkedIn More