Deep Ensembles: predictive mixtures of independently trained networks

What changed

Combines independent neural predictors trained with probabilistic losses, optional adversarial smoothing and learned regression variance into a uniform predictive mixture for uncertainty estimation.

Scientific scope

Combines independent neural predictors trained with probabilistic losses, optional adversarial smoothing and learned regression variance into a uniform predictive mixture for uncertainty estimation. Original DeepMind uncertainty recipe, not invention of ensembles, proper scoring rules or Gaussian variance prediction. Reported calibration/OOD behavior is empirical, not exact Bayesian sampling or a universal coverage certificate. Ensemble compute and storage remain.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Original DeepMind uncertainty recipe, not invention of ensembles, proper scoring rules or Gaussian variance prediction. Reported calibration/OOD behavior is empirical, not exact Bayesian sampling or a universal coverage certificate. Ensemble compute and storage remain.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction