基于学习的分布式跟踪
Learning Based Distributed Tracking
摘要:
受过去十年机器学习取得巨大成功的启发,人们一直在思考通过探索数据分布来改进理论结果的可能性。在本文中,我们重新审视了一个基本问题,称为分布式跟踪(DT)的假设下,数据遵循一定的(已知或未知)分布,并提出了一些数据相关的算法与改进的理论界。非正式地,在DT问题中,有一个协调员和k个参与者,其中协调员持有阈值N,每个参与者都有一个计数器。在每个时间戳,最多一个计数器可以增加1。协调器的工作是捕捉所有这些k个计数器的总和达到N的确切时刻。目标是最大限度地降低通信成本。虽然我们的第一种类型的算法假设具体的数据分布是预先已知的,但我们的第二种类型的算法可以动态地学习分布。这两种算法都以高概率实现了O(klogN)的通信开销,改进了现有的数据无关的O(klogN/k)的通信开销.我们进一步提出了一些实现优化算法,以提高效率和鲁棒性的算法。最后,我们在三个真实数据集和四个合成数据集上进行了广泛的实验。实验结果表明,我们的算法的通信成本是最先进的算法的至少20%。
英文摘要:
Inspired by the great success of machine learning in the past decade, people have been thinking about the possibility of improving the theoretical results by exploring data distribution. In this paper, we revisit a fundamental problem called Distributed Tracking (DT) under an assumption that the data follows a certain (known or unknown) distribution, and propose a number data-dependent algorithms with improved theoretical bounds. Informally, in the DT problem, there is a coordinator and k players, where the coordinator holds a threshold N and each player has a counter. At each time stamp, at most one counter can be increased by one. The job of the coordinator is to capture the exact moment when the sum of all these k counters reaches N. The goal is to minimise the communication cost. While our first type of algorithms assume the concrete data distribution is known in advance, our second type of algorithms can learn the distribution on the fly. Both of the algorithms achieve a communication cost bounded byO(k log log N) with high probability, improving the state-of-the-art data-independent bound O(k log N/k). We further propose a number of implementation optimisation heuristics to improve both efficiency and robustness of the algorithms. Finally, we conduct extensive experiments on three real datasets and four synthetic datasets. The experimental results show that the communication cost of our algorithms is as least as 20% of that of the state-of-the-art algorithms.
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。