PLUME: Polyhedral Learning Using Mixture of Experts
This work addresses classification tasks in machine learning, but it appears incremental as it builds on existing mixture of expert methods for a specific domain.
The paper tackles the problem of learning polyhedral classifiers by proposing a novel mixture of expert architecture, using an expectation maximization algorithm for parameter learning and deriving generalization bounds, with results showing comparable performance to state-of-the-art approaches in simulations.
In this paper, we propose a novel mixture of expert architecture for learning polyhedral classifiers. We learn the parameters of the classifierusing an expectation maximization algorithm. Wederive the generalization bounds of the proposedapproach. Through an extensive simulation study, we show that the proposed method performs comparably to other state-of-the-art approaches.