International audienceUnbounded likelihood for multivariate Gaussian mixture is an important theoretical and practical problem. Using the weak information that the latent sample size of each component has to be greater than the space dimension, we derive a simple strategy relying on non-asymptotic stochastic lower bounds for monitoring singular values of the covariance matrix of each component. Maximizing the likelihood under this data-driven constraint is proved to give consistent estimates in the univariate situation, consistency for the multivariate case being still to establish. This strategy is implemented in an EM algorithm and its excellent performance is assessed through simulated data.Le fait que la vraisemblance ne soit pas bornée...
International audienceThis correspondence derives lower bounds on the mean-square error (MSE) for th...
Finite gaussian mixture models are widely used in statistics thanks to their great flexibility. Howe...
The covariance structure of spatial Gaussian predictors (aka Kriging predictors) is generally model...
International audienceUnbounded likelihood for multivariate Gaussian mixture is an important theoret...
In the case of univariate Gaussian mixtures, unbounded likelihood is an important theoretical and pr...
In the case of univariate Gaussian mixtures, unbounded likelihood is an important theoretical and pr...
Presented at MaxEnt01. To appear in Bayesian Inference and Maximum Entropy Methods, B. Fry (Ed.), AI...
An estimation of parameters of a multivariate Gaussian Mixture Model is usually based on a criterion...
EM algorithms for multivariate normal mixture decomposition have been recently proposed in order to ...
The likelihood function for normal multivariate mixtures may present both local spurious maxima and ...
International audienceThis contribution is devoted to the estimation of the parameters of multivaria...
In the context of the univariate Gaussian mixture with grouped data, it is shown that the global max...
Gaussian mixture models (GMM), commonly used in pattern recognition and machine learning, provide a ...
Abstract —This contribution is devoted to the estimation of the parameters of multivariate Gaussian ...
This article studies the asymptotic behavior of Kernel Least Square Support Vector Machine in the co...
International audienceThis correspondence derives lower bounds on the mean-square error (MSE) for th...
Finite gaussian mixture models are widely used in statistics thanks to their great flexibility. Howe...
The covariance structure of spatial Gaussian predictors (aka Kriging predictors) is generally model...
International audienceUnbounded likelihood for multivariate Gaussian mixture is an important theoret...
In the case of univariate Gaussian mixtures, unbounded likelihood is an important theoretical and pr...
In the case of univariate Gaussian mixtures, unbounded likelihood is an important theoretical and pr...
Presented at MaxEnt01. To appear in Bayesian Inference and Maximum Entropy Methods, B. Fry (Ed.), AI...
An estimation of parameters of a multivariate Gaussian Mixture Model is usually based on a criterion...
EM algorithms for multivariate normal mixture decomposition have been recently proposed in order to ...
The likelihood function for normal multivariate mixtures may present both local spurious maxima and ...
International audienceThis contribution is devoted to the estimation of the parameters of multivaria...
In the context of the univariate Gaussian mixture with grouped data, it is shown that the global max...
Gaussian mixture models (GMM), commonly used in pattern recognition and machine learning, provide a ...
Abstract —This contribution is devoted to the estimation of the parameters of multivariate Gaussian ...
This article studies the asymptotic behavior of Kernel Least Square Support Vector Machine in the co...
International audienceThis correspondence derives lower bounds on the mean-square error (MSE) for th...
Finite gaussian mixture models are widely used in statistics thanks to their great flexibility. Howe...
The covariance structure of spatial Gaussian predictors (aka Kriging predictors) is generally model...