===== Erratum: SGDQN is Less Careful than Expected =====

//Abstract//:
The SGDQN algorithm described in [[:papers:bordes-bottou-gallinari-2009|(Bordes et al., 2009)]] 
contains a subtle ﬂaw that prevents it from reaching its design goals. 
Yet the ﬂawed SGDQN algorithm has worked well enough to be a
winner of the ﬁrst Pascal Large Scale Learning Challenge (Sonnenburg et al., 2008). This document
clariﬁes the situation, proposes a corrected algorithm, and evaluates its performance.


<box 99% orange>
Antoine Bordes, Léon Bottou, Patrick Gallinari, Jonathan Chang and S. Alex Smith:  **Erratum: SGDQN is Less Careful than Expected**,  //Journal of Machine Learning Research//, 11:2229--2240, Aug 2010.

[[http://jmlr.csail.mit.edu/papers/v11/bordes10a.html|JMLR Link]]
<html>&nbsp;&nbsp;</html>
[[http://leon.bottou.org/publications/djvu/jmlr-2010.djvu|jmlr-2010.djvu]]
[[http://leon.bottou.org/publications/pdf/jmlr-2010.pdf|jmlr-2010.pdf]]
[[http://leon.bottou.org/publications/psgz/jmlr-2010.ps.gz|jmlr-2010.ps.gz]]
</box>

  @article{bordes-2010,
    author = {Bordes, Antoine and Bottou, L\'{e}on and Gallinari, Patrick 
              and Chang, Jonathan and Smith, S. Alex},
    title = {Erratum: SGDQN is Less Careful than Expected},
    journal = {Journal of Machine Learning Research},
    year = {2010},
    volume = {11},
    pages = {2229--2240},
    month = {Aug},
    url = {http://leon.bottou.org/papers/bordes-2010},
  }

==== Remark ====

This paper started as an small erratum for 
[[:papers:bordes-bottou-gallinari-2009|(Bordes et al., 2009)]]
and eventually morphed into a full contribution subjected to the normal review process.