Physical Sciences and Mathematics Commons^™

Bayesian network (BN) parameter learning from incomplete data can be a computationally expensive task for incomplete data. Applying the EM algorithm to learn BN parameters is unfortunately susceptible to local optima and prone to premature convergence. We develop and experiment with two methods for improving EM parameter learning by using MapReduce: Age-Layered Expectation Maximization (ALEM) and Multiple Expectation Maximization (MEM). Leveraging MapReduce for distributed machine learning, these algorithms (i) operate on a (potentially large) population of BNs and (ii) partition the data set as is traditionally done with MapReduce machine learning. For example, we achieved gains using the Hadoop implementation …

This work applies the distributed computing framework MapReduce to Bayesian network parameter learning from incomplete data. We formulate the classical Expectation Maximization (EM) algorithm within the MapReduce framework. Analytically and experimentally we analyze the speed-up that can be obtained by means of MapReduce. We present details of the MapReduce formulation of EM, report speed-ups versus the sequential case, and carefully compare various Hadoop cluster configurations in experiments with Bayesian networks of different sizes and structures.

This paper considers the problem of providing, for computational processes, soft real-time (or reactive) response without the use of a hard real-time operating system. In particular, we focus on the problem of reactively computing fault diagnosis by means of different Bayesian network inference algorithms on non-real-time operating systems where low-criticality (background) process activity and system load is unpredictable.

To address this problem, we take in this paper a reconfigurable adaptive control approach. Computation time is modeled using an ARX model where the input consists of the maximum number of background processes allowed to run at any given time. To ensure …