提出一种公平性增强算法，实现每轮精确统计均等。
Fairness with Exponential Weights
- 基于指数加权框架，将赫格算法转化为公平上下文赌博机算法。
- 每轮保证精确统计均等，渐近后悔率与独立运行Exp4相当。
- 适用于分布变化的场景，适合数据驱动的公平分类任务。
为消除某些应用中的歧视问题，我们提出一种元算法，可将任意高效的赫格实例（或离散贝叶斯推断算法）转化为高效解决对应上下文赌博机问题的算法，并在每一轮中保证精确的统计均等。相对于任何具备统计均等性的比较器，该算法的渐近后悔率与对每个受保护特征独立运行Exp4相当。由于我们的赫格实例支持非平稳性，可处理随时间变化的统计均等分布，适用于真实人口未知、需从已有数据估计的情形。通过在线到批量转换，我们还可解决具有精确统计均等性的批量分类问题，所得结果被认为具有新颖性和重要性。
原文摘要 · Abstract (English)
Motivated by the need to remove discrimination in certain applications, we develop a meta-algorithm that can convert any efficient implementation of an instance of Hedge (or equivalently, an algorithm for discrete bayesian inference) into an efficient algorithm for the equivalent contextual bandit problem which guarantees exact statistical parity on every trial. Relative to any comparator with statistical parity, the resulting algorithm has the same asymptotic regret bound as running the corresponding instance of Exp4 for each protected characteristic independently. Given that our Hedge instance admits non-stationarity we can handle a varying distribution with which to enforce statistical parity with respect to, which is useful when the true population is unknown and needs to be estimated from the data received so far. Via online-to-batch conversion we can handle the equivalent batch classification problem with exact statistical parity, giving us results that we believe are novel and important in their own right.
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。