提出机制让带私有信息的智能体诚实上报，避免因隐瞒症状影响治疗公平性。
Truthful mechanisms for linear bandit games with private contexts
- 设计线性规划机制，使个体无法通过谎报上下文获利
- 实现 $O(\ln T)$ 频率上界后悔值，优于传统方法
- 适用于医疗试验等需隐私保护的个性化推荐场景
在具有私有上下文的随机上下文老虎机博弈中，个体可能为获得更好结果而谎报自身信息。传统低后悔算法（如UCB、Thompson采样）无法保证诚实申报，最坏情况下会产生线性后悔；而传统可信算法（如探索后确定、ε-贪心）虽能确保诚实但后悔过高。本文提出一种基于线性规划的机制，在最小化偏离Thompson采样的同时保障诚实性，实现 $O(\ln T)$ 的频率上界后悔。数值实验表明其在多种分布下均表现稳健。
原文摘要 · Abstract (English)
The contextual bandit problem, where agents arrive sequentially with personal contexts and the system adapts its arm allocation decisions accordingly, has recently garnered increasing attention for enabling more personalized outcomes. However, in many healthcare and recommendation applications, agents have private profiles and may misreport their contexts to gain from the system. For example, in adaptive clinical trials, where hospitals sequentially recruit volunteers to test multiple new treatments and adjust plans based on volunteers' reported profiles such as symptoms and interim data, participants may misreport severe side effects like allergy and nausea to avoid perceived suboptimal treatments. We are the first to study this issue of private context misreporting in a stochastic contextual bandit game between the system and non-repeated agents. We show that traditional low-regret algorithms, such as UCB family algorithms and Thompson sampling, fail to ensure truthful reporting and can result in linear regret in the worst case, while traditional truthful algorithms like explore-then-commit (ETC) and $ε$-greedy algorithm incur sublinear but high regret. We propose a mechanism that uses a linear program to ensure truthfulness while minimizing deviation from Thompson sampling, yielding an $O(\ln T)$ frequentist regret. Our numerical experiments further demonstrate strong performance in multiple contexts and across other distribution families.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。