基于截断牛顿法的分布式传感器选择
Distributed Sensor Selection using a Truncated Newton Method
摘要:
我们提出了一个新的分布式算法计算截断牛顿法,其中的主对角线的Hessian计算使用的信念传播。作为这种方法的案例研究,我们研究传感器选择问题,布尔凸优化问题。我们形成两个分布式算法。第一个算法是Joshi和Boyd的内点方法的分布式版本,第二个算法是一个数量级更快的近似。作为一个例子,我们讨论了网络中的分布式异常检测。我们证明了我们的解决方案的适用性,使用合成数据和真实的流量日志收集阿比林互联网骨干。
英文摘要:
We propose a new distributed algorithm for computing a truncated Newton method, where the main diagonal of the Hessian is computed using belief propagation. As a case study for this approach, we examine the sensor selection problem, a Boolean convex optimization problem. We form two distributed algorithms. The first algorithm is a distributed version of the interior point method by Joshi and Boyd, and the second algorithm is an order of magnitude faster approximation. As an example application we discuss distributed anomaly detection in networks. We demonstrate the applicability of our solution using both synthetic data and real traffic logs collected from the Abilene Internet backbone.
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。