New answers tagged

1 vote

How does expectation maximization relate to weighted least squares?

While applying EM on a mixture of Gaussian (like your case), part of the steps do coincide with weighted least squares. E step: Taking expectation w.r.t. $C$ on the loglikelihood results in a "...
Haotian Chen's user avatar
2 votes

Why use the EM Algorithm and not just marginalise the complete likelihood?

This is a few years old but I don't believe the current answer really covers it. What the question boils down is whether $\mathbb{E}_{p(z\mid x;\theta')}[\log p(x, z\,;\, \theta')]$ (in EM lower-bound)...
Lulu's user avatar
  • 168
0 votes

EM algorithm for mixture with latent regression?

Cluster-weighted modelling may be what you want. Not sure whether this is exactly what you have in mind, but it's a mixture of regressions with covariate-dependent weights. Mazza, A., Punzo, A., & ...
Christian Hennig's user avatar

Top 50 recent answers are included