<p><a href="https://github.com/MarcosPividori" class="user-mention">@MarcosPividori</a> I reread the paper. I think there are no errors. I guess the bound for the mean split random projection tree should contain a hollow like <code>HollowBallBound</code> for the vantage point tree.</p>

<p>Moreover, I found another paper "Random projection trees for vector quantization". The paper describes the same mean split algorithm.</p>

<p>Why do you think that 'RPTreeMean' differs from <code>BinarySpaceTree</code>?. As well as <code>BinarySpaceTree</code>, <code>RPTreeMean</code> divides the space into two parts. In contrast to <code>KDTree</code>, children of a <code>RPTreeMean</code> node may overlap. Thus, I updated traits for random projection trees.</p>

<p style="font-size:small;-webkit-text-size-adjust:none;color:#666;">&mdash;<br />You are receiving this because you are subscribed to this thread.<br />Reply to this email directly, <a href="https://github.com/mlpack/mlpack/pull/726#issuecomment-238100611">view it on GitHub</a>, or <a href="https://github.com/notifications/unsubscribe-auth/AJ4bFN_87li5hpMKMPEqh99aLwTKejLVks5qdiitgaJpZM4JOuGE">mute the thread</a>.<img alt="" height="1" src="https://github.com/notifications/beacon/AJ4bFB8_ao8Vo9v89d75uRhNDlPYdsGHks5qdiitgaJpZM4JOuGE.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/726#issuecomment-238100611"></link>
  <meta itemprop="name" content="View Pull Request"></meta>
</div>
<meta itemprop="description" content="View this Pull Request on GitHub"></meta>
</div>

<script type="application/json" data-scope="inboxmarkup">{"api_version":"1.0","publisher":{"api_key":"05dde50f1d1a384dd78767c55493e4bb","name":"GitHub"},"entity":{"external_key":"github/mlpack/mlpack","title":"mlpack/mlpack","subtitle":"GitHub repository","main_image_url":"https://assets-cdn.github.com/images/modules/aws/aws-bg.jpg","avatar_image_url":"https://cloud.githubusercontent.com/assets/143418/15842166/7c72db34-2c0b-11e6-9aed-b52498112777.png","action":{"name":"Open in GitHub","url":"https://github.com/mlpack/mlpack"}},"updates":{"snippets":[{"icon":"PERSON","message":"@lozhnikov in #726: @MarcosPividori I reread the paper. I think there are no errors. I guess the bound for the mean split random projection tree should contain a hollow like `HollowBallBound` for the vantage point tree.\r\n\r\nMoreover, I found another paper \"Random projection trees for vector quantization\". The paper describes the same mean split algorithm.\r\n\r\nWhy do you think that 'RPTreeMean' differs from `BinarySpaceTree`?. As well as `BinarySpaceTree`, `RPTreeMean` divides the space into two parts. In contrast to `KDTree`, children of a `RPTreeMean` node may overlap. Thus, I updated traits for random projection trees."}],"action":{"name":"View Pull Request","url":"https://github.com/mlpack/mlpack/pull/726#issuecomment-238100611"}}}</script>