<div dir="ltr">Team,<div><br></div><div>Do not miss this joyful event!</div><div><br></div><div>Artur<br><br><div class="gmail_quote"><div dir="ltr">---------- Forwarded message ---------<br>From: <strong class="gmail_sendername" dir="auto">Suzanne Muth</strong> <span dir="ltr"><<a href="mailto:lyonsmuth@cmu.edu">lyonsmuth@cmu.edu</a>></span><br>Date: Mon, Dec 3, 2018 at 1:42 PM<br>Subject: RI Ph.D. Thesis Defense: Matt Barnes<br>To: <a href="mailto:ri-people@cs.cmu.edu">ri-people@cs.cmu.edu</a> <<a href="mailto:ri-people@cs.cmu.edu">ri-people@cs.cmu.edu</a>><br></div><br><br>
<div dir="ltr">
<div id="m_2013523414651134965divtagdefaultwrapper" style="font-size:12pt;color:#000000;font-family:Calibri,Helvetica,sans-serif" dir="ltr">
<p style="font-family:Calibri,Helvetica,sans-serif,serif,EmojiFont"><span style="color:rgb(33,33,33);font-size:12pt">Date: 10 December 2018</span><br style="color:rgb(33,33,33);font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px">
<span style="color:rgb(33,33,33);font-size:12pt">Time: 9:00 a.m.</span><br style="color:rgb(33,33,33);font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px">
<span style="color:rgb(33,33,33);font-size:12pt">Place: GHC 8102</span><br style="color:rgb(33,33,33);font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px">
<span style="color:rgb(33,33,33);font-size:12pt">Type: Ph.D. Thesis Defense</span><br style="color:rgb(33,33,33);font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px">
<span style="color:rgb(33,33,33);font-size:12pt">Who: Matt Barnes</span><br style="color:rgb(33,33,33);font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px">
<font color="#212121" face="Calibri, Helvetica, sans-serif, serif, EmojiFont" size="3">Topic: </font><font color="#212121" face="Calibri, Helvetica, sans-serif, serif, EmojiFont" size="3"></font><span style="color:rgb(33,33,33);font-size:12pt">Learning
with Clusters</span></p>
<p style="font-family:Calibri,Helvetica,sans-serif,serif,EmojiFont"><br style="color:rgb(33,33,33);font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px">
<span style="color:rgb(33,33,33);font-size:12pt">Abstract:</span></p>
<div style="color:rgb(33,33,33);font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px">
<div><span style="font-size:12pt;font-family:Calibri,Helvetica,sans-serif">Clustering, the problem of grouping similar data, has been extensively studied since at least the 1950's. As machine learning becomes more prominent, clustering has evolved from
primarily a data analysis tool into an integrated component of complex robotic and machine learning systems, including those involving dimensionality reduction, anomaly detection, network analysis, image segmentation and classifying groups of data.</span></div>
<div><br>
</div>
<div><span style="font-size:12pt;font-family:Calibri,Helvetica,sans-serif">With this integration into multi-stage systems comes a need to better understand interactions between pipeline components. Changing parameters of the clustering algorithm will
impact downstream components and, quite unfortunately, it is usually not possible to simply backpropagate through the entire system. Instead, it is common practice to take the output of the clustering algorithm as ground truth at the next module of the pipeline.
We show this false assumption causes subtle and dangerous behavior for even the simplest systems -- empirically biasing results by upwards of 25%.</span></div>
<div><br>
</div>
<div><span style="font-size:12pt;font-family:Calibri,Helvetica,sans-serif">We address this gap by developing scalable estimators and methods to both quantify and compensate the impact of clustering errors on downstream learners. Our work is agnostic to
the choice of other components of the machine learning systems, and requires few assumptions on the clustering algorithm. Theoretical and empirical results demonstrate our methods and estimators are superior to the current naive approaches, which do not account
for clustering errors.</span></div>
<div><br>
</div>
<div><span style="font-size:12pt;font-family:Calibri,Helvetica,sans-serif">We also develop several new clustering algorithms and prove theoretical bounds for existing algorithms, to be used as inputs to our error-correction methods. Not surprisingly,
we find that learning on clusters of data is both theoretically and empirically easier as the number of clustering errors decreases. Thus, our work is two-fold. We attempt to provide the best clustering possible as well as establish how to effectively learn
on inevitably noisy clusters.</span></div>
</div>
<div style="color:rgb(33,33,33);font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px">
<span style="font-family:Calibri,Helvetica,sans-serif,serif,EmojiFont;font-size:12pt"></span></div>
<p style="margin-right:0px;margin-left:0px;font-size:15px;line-height:normal;font-family:Helvetica;color:rgb(33,33,33)">
<span style="font-family:Calibri,Helvetica,sans-serif,serif,EmojiFont;font-size:12pt"></span></p>
<p style="font-family:Calibri,Helvetica,sans-serif,serif,EmojiFont"><span style="color:rgb(33,33,33)"></span><font face="Calibri, Helvetica, sans-serif, serif, EmojiFont"><br style="color:rgb(33,33,33)">
</font><span style="color:rgb(33,33,33);font-size:12pt">Thesis Committee Members:</span><br style="color:rgb(33,33,33);font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px">
Artur Dubrawski, Chair</p>
<p style="font-family:Calibri,Helvetica,sans-serif,serif,EmojiFont">Geoff Gordon</p>
<p style="font-family:Calibri,Helvetica,sans-serif,serif,EmojiFont">Kris Kitani</p>
<p style="font-family:Calibri,Helvetica,sans-serif,serif,EmojiFont">Beka Steorts, Duke University</p>
<p style="font-family:Calibri,Helvetica,sans-serif,serif,EmojiFont"></p>
<p style="font-family:Calibri,Helvetica,sans-serif,serif,EmojiFont"><br style="color:rgb(33,33,33);font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px">
<span style="color:rgb(33,33,33);font-size:12pt">A copy of the thesis document is available at: </span></p>
<p style="font-family:Calibri,Helvetica,sans-serif,serif,EmojiFont"><u style="color:rgb(51,103,214);font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px"><a href="http://goo.gl/cNPSfY" rel="noopener noreferrer" id="m_2013523414651134965LPlnk892914" target="_blank">goo.gl/cNPSfY</a></u><span style="color:rgb(33,33,33);font-size:12pt"><br>
</span></p>
<p style="font-family:Calibri,Helvetica,sans-serif,serif,EmojiFont"></p>
<div id="m_2013523414651134965Signature">
<div name="divtagdefaultwrapper">
<font size="2"></font></div>
</div>
</div>
</div>
</div></div></div>