Regression with an Ensemble of Noisy Base Functions

Ensemble methods achieve state-of-the-art performance in many real-world regression problems while enjoying structural compatibility for modern decentralized computing architectures. However, the implementation of ensemble regression on distributed systems may compromise its cutting-edge performance due to computing and communication reliability issues. This paper introduces robust ensemble combining techniques designed to integrate multiple noisy predictions into a single reliable prediction. Experiments conducted with synthetic and real-world datasets in various noise regimes illustrate our robust methods' superiority over non-robust counterparts.