We consider the problem of fairly allocating items to a set of individuals, when the items are arriving online. A central solution concept in fair allocation is competitive equilibrium: every individual is endowed with a budget of faux currency, and the resulting competitive equilibrium is used to allocate. For the online fair allocation context, the PACE algorithm of Gao et al. [2021] leverages the dual averaging algorithm to approximate competitive equilibria. The authors show that, when items arrive i.i.d, the algorithm asymptotically achieves the fairness and efficiency guarantees of the offline competitive equilibrium allocation. However, real-world data is typically not stationary. One could instead model the data as adversarial, but this is often too pessimistic in practice. Motivated by this consideration, we study an online fair allocation setting with nonstationary item arrivals. To address this setting, we first develop new online learning results for the dual averaging algorithm under nonstationary input models. We show that the dual averaging iterates converge in mean square to both the underlying optimal solution of the "true" stochastic optimization problem as well as the "hindsight" optimal solution of the finite-sum problem given by the sample path. Our results apply to several nonstationary input models: adversarial corruption, ergodic input, and block-independent (including periodic) input. Here, the bound on the mean square error depends on a nonstationarity measure of the input. We recover the classical bound when the input data is i.i.d. We then show that our dual averaging results imply that the PACE algorithm for online fair allocation simultaneously achieves "best of both worlds" guarantees against any of these input models. Finally, we conduct numerical experiments which show strong empirical performance against nonstationary inputs.
翻译:当项目到达网上时,我们考虑将项目公平分配给一组个人的问题。公平分配的中央解决方案概念是竞争性均衡:每个人都拥有折合货币的预算,因此产生的竞争性平衡被用来分配。对于在线公平分配环境,加奥等人的PACE算法[2021]将双平均算法用于接近竞争性平衡。作者们显示,当项目到达i.d.d时,算法即实现了离线竞争性均衡分配的公平和效率保障。然而,现实世界数据通常不是固定的。一个人可以将数据模拟为对立的数据分配,但在实践中,这往往过于悲观。在这种考虑的推动下,我们研究一个在线公平分配设置,使用非静态项目到达时,我们首先为非静态投入模式下的双平均算算法开发新的在线学习结果。我们这里的双正正比值将“正比值”的正比值与“正对正比”的双正正比值输入方法相趋一致。我们给出了“正比”的优化问题,作为非正比值模型, 也就是“正比值” 将“正比值的计算结果”, 我们的计算结果显示“正比值输入结果显示“正比值输入结果”, 以及“正比值” 双位计算结果显示“正比值输入结果“正比值输入结果”, 显示“正比值输入结果” 和“正比值” 显示“正比值” 和“我们数”, 的计算结果“我们数“正值输入结果”, 的计算法计算法计算法计算法计算法计算法计算法计算法计算结果显示“我们数”,, 显示“正值的计算结果, 显示“正值” 显示“正值输入结果显示“我们的计算结果显示, 显示“ 显示“我们数” 显示为“ 显示“ ”, 显示“正值”, 显示“正值输入结果” 显示“正值输入结果”, 显示“正值”, 显示“我们的计算法计算法” 显示“ 的计算法”, 显示“正数” 显示“正数” 显示“正值” 显示“正值” 显示“正值” 显示“正值” 的“