---
title: "Optimal Learning in Fairness-Aware Contextual Bandits"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.00979v1"
permalink: "https://feed.astralor.com/items/itm_64f6418eac2b1b9e9749002c"
published: "2026-10-31T14:22:01.000Z"
score: 57
channel: "tech"
tags: ["Optimal Learning","Fairness-Aware Contextual Bandits","Mitigating","Lipschitz","For","UCB"]
---

# Optimal Learning in Fairness-Aware Contextual Bandits

## 速览

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{dwork201…

## 关键点

- 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.

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_64f6418eac2b1b9e9749002c