Diversity and Generalization in Neural Network Ensembles

Author name not available (Why is that?)

Publication date: 26 October 2021

Abstract: Ensembles are widely used in machine learning and, usually, provide state-of-the-art performance in many prediction tasks. From the very beginning, the diversity of an ensemble has been identified as a key factor for the superior performance of these models. But the exact role that diversity plays in ensemble models is poorly understood, specially in the context of neural networks. In this work, we combine and expand previously published results in a theoretically sound framework that describes the relationship between diversity and ensemble performance for a wide range of ensemble methods. More precisely, we provide sound answers to the following questions: how to measure diversity, how diversity relates to the generalization error of an ensemble, and how diversity is promoted by neural network ensemble algorithms. This analysis covers three widely used loss functions, namely, the squared loss, the cross-entropy loss, and the 0-1 loss; and two widely used model combination strategies, namely, model averaging and weighted majority vote. We empirically validate this theoretical analysis with neural network ensembles.

Has companion code repository: https://github.com/PGM-Lab/2022-AISTATS-diversity

This page was built for publication: Diversity and Generalization in Neural Network Ensembles

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6381332)