Metraipolis › archive › dc_d33b100676f2

Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators — arXiv:2608.07630

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.07630
License (as archived)
CC0-1.0
Archived
2026-10-19T09:02:43.565Z
SHA-256 of the archived text
b91f0f578b19049fe55f414f1be3cb28f186bc3f09e6b1e64f1278d0cf1e0f7e
Stable URL of this page
https://metraipolis.com/documento/dc_d33b100676f2

How to cite

Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators — arXiv:2608.07630 — arXiv (en), https://arxiv.org/abs/2608.07630 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d33b100676f2 (Metraipolis archive dc_d33b100676f2, sha256 b91f0f578b19049fe55f414f1be3cb28f186bc3f09e6b1e64f1278d0cf1e0f7e)
BibTeX
@misc{dcd33b100676f2,
  title = {Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators — arXiv:2608.07630},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.07630},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d33b100676f2; sha256 b91f0f578b19049fe55f414f1be3cb28f186bc3f09e6b1e64f1278d0cf1e0f7e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07630. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-11 in stat.ML).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2608.07630 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T09:01:32.143Z dalla pagina https://arxiv.org/catchup/stat.ML/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).