Metraipolis › archive › dc_6f548ec116a2

Optimal Learning in Fairness-Aware Contextual Bandits — arXiv:2611.00979

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.00979
License (as archived): CC0-1.0
Archived: 2026-11-03T11:24:58.828Z
SHA-256 of the archived text: bd86b513044eb67e2bacdfa160e00a7356dee1d408a312c5ed41e214b222265a
Stable URL of this page: https://metraipolis.com/documento/dc_6f548ec116a2

How to cite

Optimal Learning in Fairness-Aware Contextual Bandits — arXiv:2611.00979 — arXiv (en), https://arxiv.org/abs/2611.00979 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6f548ec116a2 (Metraipolis archive dc_6f548ec116a2, sha256 bd86b513044eb67e2bacdfa160e00a7356dee1d408a312c5ed41e214b222265a)

BibTeX

@misc{dc6f548ec116a2,
  title = {Optimal Learning in Fairness-Aware Contextual Bandits — arXiv:2611.00979},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00979},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6f548ec116a2; sha256 bd86b513044eb67e2bacdfa160e00a7356dee1d408a312c5ed41e214b222265a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00979. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Mitigating unfair disparities in sequential decision-making is a growing concern in machine learning. We study contextual bandits under a global covariate-based Lipschitz fairness constraint, pioneered by \cite{dwork2012fairness}, requiring individuals with similar contexts to receive similar action distributions. We show that this constraint induces a randomisation region near the decision boundary and explicitly quantify the population level cost of fairness. We further establish a canonical representation of the optimal fair policy, which reduces the fair policy design to a lower-dimensional boundary optimisation problem. We develop a lazy fair greedy algorithm that exploits fairness-induced covariate diversity under continuous contexts, with policy updates computed via finite-dimensional linear programming. For general context distributions, including discrete and mixed contexts, we propose a lazy polyhedral upper confidence bound (UCB) algorithm, whose optimistic optimisation reduces to finitely many linear programs over confidence-set vertices. Both methods satisfy fairness at every round and achieve regret of order $O(\sqrt{T} + T^{(d-2)/(d-1)}{\indc\{d\geq 4\}})$ up to poly-logarithmic factors, where $d$ is the dimension of the contexts. A matching minimax lower bound for $\ell_1$-based fairness establishes optimality, and reveals an unavoidable nonparametric cost of learning the decision boundary, which dominates the parametric learning cost when $d \geq 4$. Experiments on synthetic and real data support our theoretical findings and demonstrate the practical effectiveness of our methods.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Statistics Theory (math.ST) ; Machine Learning (cs.LG); Methodology (stat.ME); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.00979 — 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 2026-11-03T11:02:37.797Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).