<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=utf-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<p><br>
</p>
<div class="moz-forward-container"><br>
<br>
-------- Mensaje reenviado --------
<table class="moz-email-headers-table" cellspacing="0"
cellpadding="0" border="0">
<tbody>
<tr>
<th nowrap="nowrap" valign="BASELINE" align="RIGHT">Asunto:
</th>
<td>Charla sobre Clustering - M. Tepper - martes 21/11-16hs</td>
</tr>
<tr>
<th nowrap="nowrap" valign="BASELINE" align="RIGHT">Fecha: </th>
<td>Mon, 13 Nov 2017 10:04:37 -0300</td>
</tr>
<tr>
<th nowrap="nowrap" valign="BASELINE" align="RIGHT">De: </th>
<td>Mauricio Delbracio <a class="moz-txt-link-rfc2396E" href="mailto:mdelbra@gmail.com"><mdelbra@gmail.com></a></td>
</tr>
<tr>
<th nowrap="nowrap" valign="BASELINE" align="RIGHT">A: </th>
<td>todos iie <a class="moz-txt-link-rfc2396E" href="mailto:todos_iie@fing.edu.uy"><todos_iie@fing.edu.uy></a>, Marcelo Fiori -
IIE - IMERL <a class="moz-txt-link-rfc2396E" href="mailto:mfiori@fing.edu.uy"><mfiori@fing.edu.uy></a>, Santiago Castro -
InCo <a class="moz-txt-link-rfc2396E" href="mailto:sacastro@fing.edu.uy"><sacastro@fing.edu.uy></a>, Hector Cancela - INCO
<a class="moz-txt-link-rfc2396E" href="mailto:cancela@fing.edu.uy"><cancela@fing.edu.uy></a>, Matias Di Martino
<a class="moz-txt-link-rfc2396E" href="mailto:matiasdm@fing.edu.uy"><matiasdm@fing.edu.uy></a>, Diego Armentano
<a class="moz-txt-link-rfc2396E" href="mailto:diego@cmat.edu.uy"><diego@cmat.edu.uy></a>, Guillermo Moncecchi
<a class="moz-txt-link-rfc2396E" href="mailto:gmonce@fing.edu.uy"><gmonce@fing.edu.uy></a>, Paola Bermolen
<a class="moz-txt-link-rfc2396E" href="mailto:paola@fing.edu.uy"><paola@fing.edu.uy></a>, lorena etcheverry
<a class="moz-txt-link-rfc2396E" href="mailto:lorenae@fing.edu.uy"><lorenae@fing.edu.uy></a></td>
</tr>
</tbody>
</table>
<br>
<br>
<pre>Tenemos el agrado de tener de visita a Mariano Tepper, investigador
del grupo de neurociencia del Flatiron Institute (Simons Foundation) y
amigo de la casa.
Mariano dará una charla sobre su trabajo actual, que muchos de ustedes
(espero) encontrarán de interés.
"Clustering is semidefinitely not that hard", martes 21/11 a las 16hs.
Sala de seminarios del Instituto de Física (7mo piso FING)
Abajo +información. Favor reenviar a interesados.
saludos,
mauricio
---
Title:
Clustering is semidefinitely not that hard
Abstract:
In recent years, semidefinite programs (SDP) have been the subject of
interesting research in the field of clustering. In many cases, these
convex programs deliver the same answers as non-convex alternatives
and come with a guarantee of optimality. In this talk, I will argue
that SDP-KM, a popular semidefinite relaxation of K-means, can learn
manifolds present in the data, something not possible with the
original K-means formulation. To build an intuitive understanding of
SDP-KM's manifold learning capabilities, I will present a theoretical
analysis on an idealized dataset. Additionally, SDP-KM even segregates
linearly non-separable manifolds. As generic SDP solvers are slow on
large datasets, I will also discuss the suitability of efficient
algorithms to SDP-KM. These features render SDP-KM a versatile and
interesting tool for manifold learning while remaining amenable to
theoretical analysis.
Bio:
Mariano Tepper is currently a member of the neuroscience group at the
Center for Computational Biology, Flatiron Institute. His research
focuses on image processing, computer vision, pattern recognition, and
machine learning. Previously, he was a research scientist at Duke
University. Prior to working at Duke, he was postdoctoral research
associate at the University of Minnesota. Tepper holds a Ph.D. and
licentiate degree in computer science from the Universidad de Buenos
Aires in Argentina and an M.S. in applied mathematics from the École
Normale Supérieure de Cachan in France.
</pre>
</div>
</body>
</html>