We study nonstationary Online Linear Programming (OLP), where $n$ orders arrive sequentially with reward-resource consumption pairs that form a sequence of independent, but not necessarily identically distributed, random vectors. At the beginning of the planning horizon, the decision-maker is provided with a resource endowment that is sufficient to fulfill a significant portion of the requests. The decision-maker seeks to maximize the expected total reward by making immediate and irrevocable acceptance or rejection decisions for each order, subject to this resource endowment. We focus on the challenging single-sample setting, where only one sample from each of the $n$ distributions is available at the start of the planning horizon.
We propose a novel re-solving algorithm that integrates a dynamic programming perspective with the dual-based frameworks traditionally employed in stationary environments. In the large-resource regime, where the resource endowment scales linearly with the number of orders, we prove that our algorithm achieves $O((\log n)^2)$ regret across a broad class of nonstationary distribution sequences. Our results demonstrate that polylogarithmic regret is attainable even under significant environmental shifts and minimal data availability, bridging the gap between stationary OLP and more volatile real-world resource allocation problems.
Tight Regret Bounds for Stochastic Combinatorial Semi-Bandits
Adobe Research(Adobe研究院);Yahoo Labs(雅虎实验室);Technicolor Labs(Technicolor实验室);University of Alberta(阿尔伯塔大学)
随机组合半强盗是一个在线学习问题,其中在每一步中,学习代理选择一个受约束的基础项目的子集,然后观察这些项目的随机权重,并接收它们的总和作为回报。在本文中,我们关闭的问题,计算和样本有效学习的随机组合半土匪。特别是,我们分析了一个类似UCB的算法来解决这个问题,这是已知的计算效率,并证明$O(K L (1 / Δ) \log n)$和$O(\sqrt{K L n \log n})$上界的$n$ -步遗憾,其中$L$是地面项目的数量,$K$是最大数量的选择项目,和$Δ$是最佳和最佳次优解决方案的预期收益之间的差距。间隙依赖性结合紧密到常数因子,而无间隙结合紧密到多对数因子。
Tight Regret Bounds for Fixed-Price Bilateral Trade
Shanghai Jiao Tong University(上海交通大学);Huawei’s Taylor Lab(华为泰勒实验室);Shanghai University of Finance and Economics, Laboratory of Interdisciplinary Research of Computation and Economics (SUFE)(上海金融学院,计算与经济学交叉研究实验室(SUFE))
Momentum LMS Theory beyond Stationarity: Stability, Tracking, and Regret
School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences(中国科学院大学先进交叉学科学院);State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学科学国家重点实验室);School of Mathematical Sciences, University of Chinese Academy of Sciences(中国科学院大学数学科学学院)
Beyond Non-Degeneracy: Revisiting Certainty Equivalent Heuristic for Online Linear Programming
School of Data Science, the Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)数据科学学院);Data Science and Analytics Thrust, Information Hub, the Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)信息枢纽数据科学与分析学域)