\begin{thebibliography}{1}

\bibitem{duchi2011adaptive}
John Duchi, Elad Hazan, and Yoram Singer.
\newblock Adaptive subgradient methods for online learning and stochastic
  optimization.
\newblock {\em The Journal of Machine Learning Research}, 12:2121--2159, 2011.

\bibitem{golovin2013large}
Daniel Golovin, D~Sculley, H~Brendan McMahan, and Michael Young.
\newblock Large-scale learning with less ram via randomization.
\newblock {\em arXiv preprint arXiv:1303.4664}, 2013.

\bibitem{mcmahan2011follow}
H~Brendan McMahan.
\newblock Follow-the-regularized-leader and mirror descent: Equivalence
  theorems and l1 regularization.
\newblock In {\em International Conference on Artificial Intelligence and
  Statistics}, pages 525--533, 2011.

\bibitem{mcmahan2010adaptive}
H~Brendan McMahan and Matthew Streeter.
\newblock Adaptive bound optimization for online convex optimization.
\newblock {\em arXiv preprint arXiv:1002.4908}, 2010.

\bibitem{xiao2010dual}
Lin Xiao et~al.
\newblock Dual averaging methods for regularized stochastic learning and online
  optimization.
\newblock {\em Journal of Machine Learning Research}, 11(2543-2596):4, 2010.

\end{thebibliography}