Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of Experts

Originally introduced as a neural network for ensemble learning, mixture of experts (MoE) has recently become a fundamental building block of highly successful modern deep neural networks for heterogeneous data analysis in several applications of machine learning and statistics. Despite its popularity in practice, a satisfactory level of theoretical understanding of the MoE model is far from complete. To shed new light on this problem, we provide a convergence analysis for maximum likelihood estimation (MLE) in the Gaussian-gated MoE model. …

analysis applications become block building convergence cs.lg data data analysis ensemble experts machine machine learning mixture of experts modern moe network networks neural network neural networks practice statistics stat.ml