Hi, thanks for the response,<br>
This might be a dumb question but does FastMKS gracefully handle sparse<br>
vectors ? I saw in your history that you rely on Armadillo for sparse<br>
matrix handling, does the FastMKS implementation work with that ?<br>
On Mar 30, 2015 12:30 AM, "Ryan Curtin" <notifications@github.com> wrote:<br>
<br>
> Hi there,<br>
><br>
> The exact MIPS algorithm with the cone tree actually isn't in mlpack, so<br>
> the paper is incorrect. However, I bet Parikshit has an implementation<br>
> somewhere, which could be polished and added to mlpack (you can email him:<br>
> p.ram@gatech.edu; whatever code he gives you, I can help you make it<br>
> compile and work, and possibly just adapt and add it to mlpack so the paper<br>
> is correct).<br>
><br>
> On the other hand, what we do have implemented is FastMKS, which solves<br>
> inner-product search in a more general sense (<br>
> http://ratml.org/pub/pdf/2014fastmks.pdf). Here's a tutorial on how to<br>
> use it in mlpack: http://mlpack.org/doxygen.php?doc=fmkstutorial.html .<br>
> Perhaps that would be useful to you too? I don't know how it will perform<br>
> for nearest neighbor---our FastMKS implementation doesn't (currently) use<br>
> cone trees.<br>
><br>
> —<br>
> Reply to this email directly or view it on GitHub<br>
> <https://github.com/mlpack/mlpack/issues/427#issuecomment-87538445>.<br>
><br>
<p style="font-size:small;-webkit-text-size-adjust:none;color:#666;">—<br>Reply to this email directly or <a href="https://github.com/mlpack/mlpack/issues/427#issuecomment-87539296">view it on GitHub</a>.<img alt="" height="1" src="https://github.com/notifications/beacon/AJ4bFGG8f0tCguLcZW-Fci9-p46fEBJrks5n6MpLgaJpZM4D2zmd.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/427#issuecomment-87539296"></link>
<meta itemprop="name" content="View Issue"></meta>
</div>
<meta itemprop="description" content="View this Issue on GitHub"></meta>
</div>