<p>SGD for LR-SDP is becoming more popular, and this paper <a href="http://arxiv.org/pdf/1411.1134v2.pdf">http://arxiv.org/pdf/1411.1134v2.pdf</a> lays the groundwork for some neat theoretical convergence results (in particular, how to choose step sizes). This is really cool stuff which we should investigate. </p>

<p style="font-size:small;-webkit-text-size-adjust:none;color:#666;">&mdash;<br>Reply to this email directly or <a href="https://github.com/mlpack/mlpack/issues/395">view it on GitHub</a>.<img alt="" height="1" src="https://github.com/notifications/beacon/AJ4bFOQIaYC978yAYk7QvkMSR5VvQ98Zks5nnH6TgaJpZM4DZ2uG.gif" width="1" /></p>
<div itemscope itemtype="http://schema.org/EmailMessage">
  <div itemprop="action" itemscope itemtype="http://schema.org/ViewAction">
    <link itemprop="url" href="https://github.com/mlpack/mlpack/issues/395"></link>
    <meta itemprop="name" content="View Issue"></meta>
  </div>
  <meta itemprop="description" content="View this Issue on GitHub"></meta>
</div>