====== SGDQN ======

The [[:papers:bordes-bottou-gallinari-2009|SGDQN]] paper has been published 
on the [[http://jmlr.csail.mit.edu/papers/v10/bordes09a.html|JMLR site]].
This variant of [[:research:stochastic|stochastic gradient]] got very good results
during the first [[http://largescale.first.fraunhofer.de/workshop/|PASCAL Large Scale Learning Challenge]].
The paper gives a lot of explanation on the design of the algorithm.
Source code is available from [[http://webia.lip6.fr/~bordes/mywiki/doku.php?id=sgdqn|Antoine's]] web site.