Approximations of conditional probability density functions in Lebesgue spaces via mixture of experts models
arXiv:2012.02385 · doi:10.1186/s40488-021-00125-0
Abstract
Mixture of experts (MoE) models are widely applied for conditional probability density estimation problems. We demonstrate the richness of the class of MoE models by proving denseness results in Lebesgue spaces, when inputs and outputs variables are both compactly supported. We further prove an almost uniform convergence result when the input is univariate. Auxiliary lemmas are proved regarding the richness of the soft-max gating function class, and their relationships to the class of Gaussian gating functions.
arXiv commentCorrected typos. Added new Section 6. Summary and conclusions
References in corpus (7)
- Model-based clustering via linear cluster-weighted models
- Joint segmentation of multivariate time series with hidden process regression for human activity recognition
- Approximation by finite mixtures of continuous density functions that vanish at infinity
- Acoustic Space Learning for Sound Source Separation and Localization on Binaural Manifolds
- High-Dimensional Regression with Gaussian Mixtures and Partially-Latent Response Variables
- Approximation of conditional densities by smooth mixtures of regressions
- Robust mixture of experts modeling using the distribution