[Numpy-discussion] performance matrix multiplication vs. matlab

[David Cournapeau]

Jason Rennie wrote:
> Note that EM can be very slow to converge:
>
> http://www.cs.toronto.edu/~roweis/papers/emecgicml03.pdf
> <http://www.cs.toronto.edu/%7Eroweis/papers/emecgicml03.pdf>
>
> EM is great for churning-out papers, not so great for getting real
> work done.

I think it depends on what you are doing - EM is used for 'real' work
too, after all :)

> Conjugate gradient is a much better tool, at least in my (and
> Salakhutdinov's) experience.

Thanks for the link, I was not aware of this work. What is the
difference between the ECG method and the method proposed by Lange in
[1] ? To avoid 'local trapping' of the parameter in EM methods,
recursive EM [2] may also be a promising method, also it seems to me
that it has not been used so much, but I may well be wrong (I have seen
several people using a simplified version of it without much theoretical
consideration in speech processing).

cheers,

David

[1] "A gradient algorithm locally equivalent to the EM algorithm", in
Journal of the Royal Statistical Society. Series B. Methodological,
1995, vol. 57, n^o 2, pp. 425-437
[2] "Online EM Algorithm for Latent Data Models", by: Olivier Cappe;,
Eric Moulines, in the Journal of the Royal Statistical Society Series B
(February 2009).