We consider the problem of asynchronous online combinatorial optimization on a network of communicating agents. At each time step, some of the agents are stochastically activated, requested to make a prediction, and the system pays the corresponding loss. Then, neighbors of active agents receive semi-bandit feedback and exchange some succinct local information. The goal is to minimize the network regret, defined as the difference between the cumulative loss of the predictions of active agents and that of the best action in hindsight, selected from a combinatorial decision set. The main challenge in such a context is to control the computational complexity of the resulting algorithm while retaining minimax optimal regret guarantees. We introduce Coop-FTPL, a cooperative version of the well-known Follow The Perturbed Leader algorithm, that implements a new loss estimation procedure generalizing the Geometric Resampling of Neu and Bart{\'o}k [2013] to our setting. Assuming that the elements of the decision set are k-dimensional binary vectors with at most m non-zero entries and $\alpha$ 1 is the independence number of the network, we show that the expected regret of our algorithm after T time steps is of order Q mkT log(k)(k$\alpha$ 1 /Q + m), where Q is the total activation probability mass. Furthermore, we prove that this is only $\sqrt$ k log k-away from the best achievable rate and that Coop-FTPL has a state-of-the-art T 3/2 worst-case computational complexity.
翻译:我们考虑的是通信代理商网络上的不同步在线组合优化问题。 在每一个步骤中, 某些代理商都会被快速启动, 被要求做出预测, 系统会支付相应的损失。 然后, 活跃代理商的邻居会收到半弯曲反馈, 并交换一些简洁的本地信息。 目标是将网络的遗憾降到最低程度, 即活动代理商预测的累积损失与从组合式决定集中选择的后视中的最佳动作之间的差别。 在这样的背景下, 主要的挑战是控制由此产生的算法的计算复杂性, 同时保留微量计算法的最佳遗憾保证。 我们引入Coop- FTPL, 这是众所周知的“ 跟踪隐蔽的领头算法” 合作版本, 实施新的损失估算程序, 将Eeu和Bart_ofrk [2013] 的几何标准推广到我们的设置范围。 假设决定集的元素是k- 维度的二进量矢矢量, 最差的条目和 $\alpha$ 1 是网络的独立 Q 。 我们所预期的轨道 ral_ ral_ ral_ ral_ ral_ ral_ ral