<p>Joseph is right, we don't have to save the input, output and gradient parameter. We don't need the parameter for optimizing an already trained model nor for testing.</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/pull/516#issuecomment-183068885">view it on GitHub</a>.<img alt="" height="1" src="https://github.com/notifications/beacon/AJ4bFMZkKj8z2EgKoQL-QiPPUH0rFU-Sks5pjPdIgaJpZM4HTzyk.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/pull/516#issuecomment-183068885"></link>
  <meta itemprop="name" content="View Pull Request"></meta>
</div>
<meta itemprop="description" content="View this Pull Request on GitHub"></meta>
</div>