Metraipolis › archive › dc_1fd981624331

Classification with Abstention Under Class-Conditional Error Constraints — arXiv:2609.22632

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22632
License (as archived)
CC0-1.0
Archived
2026-10-09T07:06:45.412Z
SHA-256 of the archived text
15baf245d9c3d862507db03e91c2796d8c869c549f270050ded62919606095e5
Stable URL of this page
https://metraipolis.com/documento/dc_1fd981624331

How to cite

Classification with Abstention Under Class-Conditional Error Constraints — arXiv:2609.22632 — arXiv (en), https://arxiv.org/abs/2609.22632 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1fd981624331 (Metraipolis archive dc_1fd981624331, sha256 15baf245d9c3d862507db03e91c2796d8c869c549f270050ded62919606095e5)
BibTeX
@misc{dc1fd981624331,
  title = {Classification with Abstention Under Class-Conditional Error Constraints — arXiv:2609.22632},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22632},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1fd981624331; sha256 15baf245d9c3d862507db03e91c2796d8c869c549f270050ded62919606095e5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22632. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study binary classification with abstention under separate class-conditional error constraints, with the objective of minimizing abstention while keeping both errors below prescribed thresholds. We characterize the distribution-free minimax rate of excess abstention risk, up to logarithmic factors, in terms of the complexity of the hypothesis class and the sample size. To make the framework amenable to computation with models such as neural networks, we introduce surrogate-loss formulations and derive finite-sample guarantees for excess surrogate ambiguity risk. We formulate the resulting learning task as a constrained optimization problem and characterize its computational complexity in the convex setting. Finally, we evaluate our approach on various datasets and compare its performance with a competing method for this problem.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.22632 — 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 2026-10-09T06:58:09.209Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).