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

[Hector Cancela]

-------- Mensaje reenviado --------
Asunto: 	Charla sobre Clustering - M. Tepper - martes 21/11-16hs
Fecha: 	Mon, 13 Nov 2017 10:04:37 -0300
De: 	Mauricio Delbracio <mdelbra at gmail.com>
A: 	todos iie <todos_iie at fing.edu.uy>, Marcelo Fiori - IIE - IMERL 
<mfiori at fing.edu.uy>, Santiago Castro - InCo <sacastro at fing.edu.uy>, 
Hector Cancela - INCO <cancela at fing.edu.uy>, Matias Di Martino 
<matiasdm at fing.edu.uy>, Diego Armentano <diego at cmat.edu.uy>, Guillermo 
Moncecchi <gmonce at fing.edu.uy>, Paola Bermolen <paola at fing.edu.uy>, 
lorena etcheverry <lorenae at 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.

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.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://www.fing.edu.uy/pipermail/posgrados-invop/attachments/20171113/fb101831/attachment.html>