arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.10469cs.GTcs.LGmath.OC
收藏

在线广义均值福利最大化:从样本中实现近最优的遗憾

Online Generalized-Mean Welfare Maximization: Achieving Near-Optimal Regret from Samples

Columbia University(哥伦比亚大学);Carnegie Mellon University(卡内基梅隆大学)

Zongjun Yang, Rachitesh Kumar, Christian Kroer

AI总结:

本文提出了一种在线广义均值福利最大化算法,在无需分布知识的情况下实现近最优的遗憾率,通过重新求解范式应对非平稳性和分布偏移。

摘要:

我们研究了在线公平分配中T个依次到达的物品在n个具有异质偏好的代理人之间的分配,目标是最大化广义均值福利,定义为代理人时间平均效用的p-均值,其中p∈(-∞,1)。我们首先考虑i.i.d.到达模型,证明纯贪婪算法——即贪心地选择效用最大化整数分配——可以实现O(1/T)的平均遗憾。值得注意的是,与先前工作不同,我们的算法不需要分布知识,并且仅使用在线样本即可达到最优的遗憾率。然后我们超越i.i.d.到达模型,研究了一个非平稳模型,具有随时间变化的独立分布。在没有关于分布的额外数据的情况下,已知每个在线算法必须遭受Ω(1)的平均遗憾。我们证明,仅从每个分布中获取一个历史样本就足以恢复最优的O(1/T)平均遗憾率,即使在面对任意非平稳性的情况下。我们的算法基于重新求解范式:它们假设剩余物品将是历史上在那些时期中看到的物品,并解决由此产生的福利最大化问题以确定每个时期的决策。最后,我们还考虑了可能扭曲历史样本忠实性的分布偏移,并展示我们的重新求解算法对这种偏移具有鲁棒性。

英文摘要:

We study online fair allocation of $T$ sequentially arriving items among $n$ agents with heterogeneous preferences, with the objective of maximizing generalized-mean welfare, defined as the $p$-mean of agents' time-averaged utilities, with $p\in (-\infty, 1)$. We first consider the i.i.d. arrival model and show that the pure greedy algorithm -- which myopically chooses the welfare-maximizing integral allocation -- achieves $\widetilde{O}(1/T)$ average regret. Importantly, in contrast to prior work, our algorithm does not require distributional knowledge and achieves the optimal regret rate using only the online samples. We then go beyond i.i.d. arrivals and investigate a nonstationary model with time-varying independent distributions. In the absence of additional data about the distributions, it is known that every online algorithm must suffer $Ω(1)$ average regret. We show that only a single historical sample from each distribution is sufficient to recover the optimal $\widetilde{O}(1/T)$ average regret rate, even in the face of arbitrary non-stationarity. Our algorithms are based on the re-solving paradigm: they assume that the remaining items will be the ones seen historically in those periods and solve the resulting welfare-maximization problem to determine the decision in every period. Finally, we also account for distribution shifts that may distort the fidelity of historical samples and show that the performance of our re-solving algorithms is robust to such shifts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑