[Todos CMAT] Fwd: Charla sobre Clustering - M. Tepper - martes 21/11-16hs

Diego Armentano diego en cmat.edu.uy
Lun Nov 13 11:13:55 -03 2017

Reenvío información sobre charla.

---------- Forwarded message ----------
From: Mauricio Delbracio <mdelbra en gmail.com>
Date: 2017-11-13 10:04 GMT-03:00
Subject: Charla sobre Clustering - M. Tepper - martes 21/11-16hs
To: todos iie <todos_iie en fing.edu.uy>, Marcelo Fiori - IIE - IMERL <
mfiori en fing.edu.uy>, Santiago Castro - InCo <sacastro en fing.edu.uy>, Hector
Cancela - INCO <cancela en fing.edu.uy>, Matias Di Martino <
matiasdm en fing.edu.uy>, Diego Armentano <diego en cmat.edu.uy>, Guillermo
Moncecchi <gmonce en fing.edu.uy>, Paola Bermolen <paola en fing.edu.uy>, lorena
etcheverry <lorenae en fing.edu.uy>

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.



Clustering is semidefinitely not that hard

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.

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.

Diego Armentano
diego en cmat.edu.uy <diegoax en gmail.com>
2 525 25 22 (109)
------------ próxima parte ------------
Se ha borrado un adjunto en formato HTML...
URL: <http://listas.cmat.edu.uy/pipermail/todos/attachments/20171113/e196a800/attachment.html>

Más información sobre la lista de distribución Todos