arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2005.14708math.OCcs.LGstat.ML
收藏

随机累积约束下的在线DR-子模极大化

Online DR-Submodular Maximization with Stochastic Cumulative Constraints

University of Washington(华盛顿大学)

Prasanna Sanjay Raut, Omid Sadeghi, Maryam Fazel

摘要:

本文研究了线性随机长期约束下的在线连续DR-子模极大化问题。与在线次模最大化的先前工作相比,我们的设置引入了随机线性约束函数的额外复杂性,这些函数是独立同分布的。在每一轮产生。确切地说,在步骤$t\in\{1,\dots,T\}$,DR-子模效用函数$f_t(\cdot)$和约束向量$p_t$,i.i.d.从具有平均$p$的未知分布中生成,在提交动作$x_t$后显示,并且我们的目标是在预期的累积资源消耗$\sum_{t=1}^T \langle p,x_t\rangle$低于固定预算$B_T$时最大化总体效用。随机长期约束自然出现在应用程序中,其中有一个有限的预算或资源可用,在每一步的资源消耗是由随机时变环境。我们提出了在线拉格朗日Frank-Wolfe(OLFW)算法来解决这类在线问题。我们分析了OLFW算法的性能,我们得到了次线性遗憾界以及次线性累积约束违反界,无论是在期望和高概率。

英文摘要:

In this paper, we consider online continuous DR-submodular maximization with linear stochastic long-term constraints. Compared to the prior work on online submodular maximization, our setting introduces the extra complication of stochastic linear constraint functions that are i.i.d. generated at each round. To be precise, at step $t\in\{1,\dots,T\}$, a DR-submodular utility function $f_t(\cdot)$ and a constraint vector $p_t$, i.i.d. generated from an unknown distribution with mean $p$, are revealed after committing to an action $x_t$ and we aim to maximize the overall utility while the expected cumulative resource consumption $\sum_{t=1}^T \langle p,x_t\rangle$ is below a fixed budget $B_T$. Stochastic long-term constraints arise naturally in applications where there is a limited budget or resource available and resource consumption at each step is governed by stochastically time-varying environments. We propose the Online Lagrangian Frank-Wolfe (OLFW) algorithm to solve this class of online problems. We analyze the performance of the OLFW algorithm and we obtain sub-linear regret bounds as well as sub-linear cumulative constraint violation bounds, both in expectation and with high probability.

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。

↑