arXiv Machine Learning August 11, 2026 By Pierre Nodet, Thomas George

Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators

Read the original on arXiv Machine Learning →

arXiv:2608. 07630v1 Announce Type: new Abstract: We adapt two classical statistical estimators for quantifying uncertainty to modern deep learning, in order to provide clearer insights into uncertainty attributable to two sources : aleatoric uncertainty, or locally scarce data.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 15

Uncertainty Estimation and Generalization Bounds for Modern Deep Learning

arXiv:2606. 13818v1 Announce Type: new Abstract: This thesis investigates how Bayesian principles can deepen our understanding of modern deep learning systems.

By Luis A. Ortega

arXiv Machine Learning

Aug 3

Cooperative Variance Estimation and Bayesian Neural Networks for Disentangling Aleatoric and Epistemic Uncertainties

arXiv:2505. 02743v3 Announce Type: replace Abstract: Real-world data contains aleatoric uncertainty - irreducible noise arising from imperfect measurements or from incomplete knowledge about the data generation process.

By Jiaxiang Yi, Miguel A. Bessa

arXiv AI

Jun 2

Possibilistic Predictive Uncertainty for Deep Learning

arXiv:2605. 00600v2 Announce Type: replace-cross Abstract: Deep neural networks achieve impressive results across diverse applications, yet their overconfidence on unseen inputs necessitates reliable epistemic uncertainty modeling.

By Yao Ni, Jeremie Houssineau, Yew Soon Ong, Piotr Koniusz

benchmarks

arXiv AI

Jun 4

Uncertainty Estimation using Variance-Gated Distributions

arXiv:2509. 08846v2 Announce Type: replace-cross Abstract: Evaluation of per-sample uncertainty quantification from neural networks is essential for decision-making involving high-risk applications.

By H. Martin Gillis, Isaac Xu, Thomas Trappenberg

Hugging Face Trending Papers

Aug 11

Fisher8: Stabilizing Neural Heteroscedastic Regression via Output-Layer Fisher Geometry

Training neural networks to jointly predict mean and uncertainty estimates from noisy observations can be unstable, prompting a series of independent stabilization efforts. We argue that these interventions highlight a common underlying issue where gradient steps are poorly aligned with the geometry of the loss landscape.

llms

arXiv Machine Learning

Aug 12

Fisher8: Stabilizing Neural Heteroscedastic Regression via Output-Layer Fisher Geometry

arXiv:2608. 10374v1 Announce Type: new Abstract: Training neural networks to jointly predict mean and uncertainty estimates from noisy observations can be unstable, prompting a series of independent stabilization efforts.

By Sumedh Vemuganti, Nickvash Kani

llms

Related stories

Uncertainty Estimation and Generalization Bounds for Modern Deep Learning

Cooperative Variance Estimation and Bayesian Neural Networks for Disentangling Aleatoric and Epistemic Uncertainties

Possibilistic Predictive Uncertainty for Deep Learning

Uncertainty Estimation using Variance-Gated Distributions

Fisher8: Stabilizing Neural Heteroscedastic Regression via Output-Layer Fisher Geometry

Fisher8: Stabilizing Neural Heteroscedastic Regression via Output-Layer Fisher Geometry