Approximations of conditional probability density functions in Lebesgue spaces via mixture of experts models
From MaRDI portal
Publication:2129248
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.
Recommendations
- Mixture of experts architectures for neural networks as a special case of conditional expectation formula.
- A universal approximation theorem for mixture-of-experts models
- Approximation of conditional densities by smooth mixtures of regressions
- Hierarchical mixtures-of-experts for exponential family regression models: Approximation and maximum likelihood estimation
- Error bounds for functional approximation and estimation using mixtures of experts
Cites work
- scientific article; zbMATH DE number 5500983 (Why is no real title available?)
- scientific article; zbMATH DE number 1324223 (Why is no real title available?)
- scientific article; zbMATH DE number 841537 (Why is no real title available?)
- A distribution-free theory of nonparametric regression
- A universal approximation theorem for mixture-of-experts models
- An \(\ell_1\)-oracle inequality for the Lasso in multivariate finite mixture of multivariate Gaussian regression models
- An introductory course in Lebesgue spaces
- Applied functional analysis
- Approximation by finite mixtures of continuous density functions that vanish at infinity
- Approximation of conditional densities by smooth mixtures of regressions
- Bayesian regression with heteroscedastic error density and parametric mean function
- Density estimation through convex combinations of densities: Approximation and estimation bounds
- Error bounds for functional approximation and estimation using mixtures of experts
- Finite mixture regression: a sparse variable selection by model selection for clustering
- Gaussian mixture vector autoregression
- Hierarchical mixtures-of-experts for exponential family regression models: Approximation and maximum likelihood estimation
- High-dimensional regression with Gaussian mixtures and partially-latent response variables
- Inverse regression approach to robust nonlinear high-to-low dimensional mapping
- Laplace mixture of linear experts
- Learning Theory
- Local statistical modeling via a cluster-weighted approach with elliptical distributions
- Mixture of Gaussian regressions model with logistic weights, a penalized maximum likelihood approach
- Model-based clustering via linear cluster-weighted models
- Nonparametric Regression Estimation by Normalized Radial Basis Function Networks
- On convergence rates of mixtures of polynomial experts
- Posterior consistency in conditional density estimation by covariate dependent mixtures
- Risk bounds for mixture density estimation
- Robust mixture of experts modeling using the \(t\) distribution
- Variable Lebesgue spaces. Foundations and harmonic analysis
Cited in
(10)- A universal approximation theorem for mixture-of-experts models
- Regression‐based heterogeneity analysis to identify overlapping subgroup structure in high‐dimensional data
- Functional mixtures-of-experts
- Approximation of probability density functions via location-scale finite mixtures in Lebesgue spaces
- Summary statistics and discrepancy measures for approximate Bayesian computation via surrogate posteriors
- A non-asymptotic approach for model selection via penalization in high-dimensional mixture of experts models
- A flexible probabilistic framework for large-margin mixture of experts
- Error bounds for functional approximation and estimation using mixtures of experts
- Mixture of experts architectures for neural networks as a special case of conditional expectation formula.
- Dealing with overdispersion in multivariate count data
This page was built for publication: Approximations of conditional probability density functions in Lebesgue spaces via mixture of experts models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2129248)
