PLUME: Polyhedral Learning Using Mixture of Experts
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Application of the Polyhedral Conic Functions Method in the Text Classification and Comparative AnalysisScientific Programming, 2018
- Polyhedral Conic Classifiers for Visual Object Detection and Classification2017
- Geometric Decision TreeIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2011
- Accurately learning from few examples with a polyhedral classifierComputational Optimization and Applications, 2007
- Polyhedral Separability Through Successive LPJournal of Optimization Theory and Applications, 2002
- Rademacher and Gaussian Complexities: Risk Bounds and Structural Results2001
- Adaptive Mixtures of Local ExpertsNeural Computation, 1991