Metraipolis › archive › dc_692fa54a20c3

Practical Estimation of the Bayes Optimal Fairness-Accuracy Tradeoff with Soft Labels — arXiv:2611.06027

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.06027
License (as archived)
CC0-1.0
Archived
2026-11-05T18:17:42.344Z
SHA-256 of the archived text
71f8f821a00d7b2252724e1bdfed9ec6939f8205f1019216869923870504bd68
Stable URL of this page
https://metraipolis.com/documento/dc_692fa54a20c3

How to cite

Practical Estimation of the Bayes Optimal Fairness-Accuracy Tradeoff with Soft Labels — arXiv:2611.06027 — arXiv (en), https://arxiv.org/abs/2611.06027 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_692fa54a20c3 (Metraipolis archive dc_692fa54a20c3, sha256 71f8f821a00d7b2252724e1bdfed9ec6939f8205f1019216869923870504bd68)
BibTeX
@misc{dc692fa54a20c3,
  title = {Practical Estimation of the Bayes Optimal Fairness-Accuracy Tradeoff with Soft Labels — arXiv:2611.06027},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06027},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_692fa54a20c3; sha256 71f8f821a00d7b2252724e1bdfed9ec6939f8205f1019216869923870504bd68},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06027. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

There is a fundamental limit to the best prediction error of any model for a given data distribution. In classification, the Bayes error quantifies this limit and serves as both a benchmark for trained models and a criterion to detect overfitting. The state-of-the-art Bayes error estimation techniques for binary classification use only soft labels (positive class probabilities) and require no input features or auxiliary training. We extend such notions to constrained classification problems, such as fairness. Fair classification is an important case of constrained or multi-objective classification. It requires a model not only to be accurate but also to yield fair outcomes (equal or near-equal true positive rates) across different demographic groups (e.g., race and gender). This leads to an inherent fairness-accuracy tradeoff or a Pareto frontier that is used to compare fair classifiers against each other. The focus of our work is to estimate the fundamental limit for this fairness-accuracy tradeoff. We derive an explicit expression for the fair Bayes error rate (i.e., best achievable error rate subject to given fairness constraints), and construct consistent, instance-free estimators for it using only soft labels and group information. We provably bound the bias and the sample complexity of our estimators. Empirically, our method produces a robust, low-variance estimate of the optimal fairness-accuracy tradeoff curve, even when the soft labels are noisy and derived from a classification model on hard labels.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.06027 — 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 2026-11-05T18:12:49.044Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).