[Topic-models] LDA paper by Blei - some more questions

Mateusz Berezecki mateuszb at gmail.com
Wed Nov 19 08:55:52 EST 2008


Hi Dave,

On Wed, Nov 19, 2008 at 2:44 PM, David Blei <blei at cs.princeton.edu> wrote:

> in the E-step, optimize variational parameters for each document and compute
> expected sufficient statistics under the resulting variational
> distributions.  this step depends on a setting of the model parameters,
> i.e.,  the dirichlet hyperparameters and topic distributions.  in the
> M-step, optimize those model parameters according to those expected
> sufficient statistics.  repeat until the bound on the log likelihood of the
> data converges.

Ok, makes perfect sense now! Thanks a lot Dave.

best,
Mateusz


More information about the Topic-models mailing list