AI News HubLIVE
Original source2 min read

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

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. Our approach leverages recent advances in approximate Fisher Information Matrices, to enable scaling to actual architectures. Experimental results demonstrate how each test points is differentially impacted by both sources, highlighting the practical utility of our estimators in improving the robustness of real-world applications.

SourcearXiv Machine LearningAuthor: Pierre Nodet, Thomas George

-->

[Submitted on 7 Aug 2026]

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

View a PDF of the paper titled Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators, by Pierre Nodet and Thomas George

View PDF HTML (experimental)

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. Our approach leverages recent advances in approximate Fisher Information Matrices, to enable scaling to actual architectures. Experimental results demonstrate how each test points is differentially impacted by both sources, highlighting the practical utility of our estimators in improving the robustness of real-world applications.

Subjects:

Machine Learning (cs.LG); Machine Learning (stat.ML)

Cite as: arXiv:2608.07630 [cs.LG]

(or arXiv:2608.07630v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2608.07630

arXiv-issued DOI via DataCite

Submission history

From: Thomas George [view email] [v1] Fri, 7 Aug 2026 12:18:52 UTC (9,181 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators, by Pierre Nodet and Thomas George

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-08

Change to browse by:

cs stat stat.ML

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)