CIF: Small: Collaborative Research: Network Event Detection with Multistream Observations

CIF：小型：协作研究：通过多流观察进行网络事件检测

• 批准号: 1801855
• 负责人: Yingbin Liang
• 金额: $ 18.43万
• 依托单位: Ohio State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-10-01 至 2021-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1801855&HistoricalAwards=false
• 关键词: CIF; Small; Collaborative; Research; Network

The goal in network event detection is to detect the existence of a set of nodes over a large network whose observations reflect the occurrence of an unusual event. Existing studies of network event detection have been mainly from two perspectives. The first is data-driven without assuming any underlying statistical model, and is typically applicable to more general data sets, but may not come with performance guarantees. The second perspective is model-driven, with certain statistical distributions (e.g., Gaussian) assumed for the data, and usually comes with performance guarantees, but may be limited to applications where the data fit the model. The goal in this project is to explore a framework for network event detection that unifies a wide range of event detection problems, in which the data are assumed to be governed by some underlying statistical distributions, but is data-driven in the sense that little is assumed a priori about the distributions. The developed detection approaches and statistical tools have a wide range of applications, including fraud detection, clinical trials, medical diagnosis, high-frequency trading, voting irregularity analysis, and network intrusion.A comprehensive approach to general network event detection problems is developed in this project through the exploration of three thrusts: (i) detection of (unstructured) point events, (ii) detection of graph-based structured events, and (iii) sequential and quickest detection of dynamically evolving graph structures. The performance of the designed tests is characterized in terms of the probability of detection error and the rate at which this error goes to zero. Various fundamental issues are addressed, including non-i.i.d. data streams, as well as the interplay between network size, event size, sample size, and data dimension.

网络事件检测的目标是检测大型网络中一组节点的存在，这些节点的观测反映了异常事件的发生。现有的网络事件检测研究主要从两个角度进行。第一种是数据驱动的，没有假设任何底层的统计模型，通常适用于更一般的数据集，但可能没有性能保证。第二种观点是模型驱动的，具有某些统计分布（例如，高斯），通常具有性能保证，但可能仅限于数据符合模型的应用程序。该项目的目标是探索一个网络事件检测框架，该框架统一了广泛的事件检测问题，其中数据被假设为由一些基本的统计分布所控制，但在某种意义上说，几乎没有关于分布的先验假设，这是数据驱动的。所开发的检测方法和统计工具具有广泛的应用，包括欺诈检测、临床试验、医疗诊断、高频交易、投票不规则性分析和网络入侵。本项目通过三个方面的探索，开发了一种综合的方法来解决一般的网络事件检测问题：（i）（非结构化）点事件的检测，（ii）基于图的结构化事件的检测，以及（iii）动态演变的图结构的顺序和最快检测。所设计的测试的性能的特征在于检测错误的概率和该错误变为零的速率。各种基本问题都得到了解决，包括非i.i.d.数据流，以及网络大小、事件大小、样本大小和数据维度之间的相互作用。

项目成果

Understanding Estimation and Generalization Error of Generative Adversarial Networks

• DOI: 10.1109/tit.2021.3053234
• 发表时间: 2021-05
• 期刊: IEEE Transactions on Information Theory
• 影响因子: 2.5
• 作者: Kaiyi Ji;Yi Zhou;Yingbin Liang

Guaranteed Recovery of One-Hidden-Layer Neural Networks via Cross Entropy

• DOI: 10.1109/tsp.2020.2993153
• 发表时间: 2018-02
• 期刊: IEEE Transactions on Signal Processing
• 影响因子: 5.4
• 作者: H. Fu;Yuejie Chi;Yingbin Liang

Sample Complexity Bounds for Two Timescale Value-based Reinforcement Learning Algorithms

• 发表时间: 2020-11
• 作者: Tengyu Xu;Yingbin Liang

When will gradient methods converge to max‐margin classifier under ReLU models?

• DOI: 10.1002/sta4.354
• 发表时间: 2018-06
• 期刊: Stat
• 影响因子: 1.7
• 作者: Tengyu Xu;Yi Zhou;Kaiyi Ji;Yingbin Liang

Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms

• 发表时间: 2020-04
• 期刊: arXiv: Learning
• 作者: Tengyu Xu;Zhe Wang-;Yingbin Liang