[Seminario] INVITACION SEMINARIO MATEMÁTICAS DISCRETAS, MIÉRCOLES 28 A LAS 14:30 HRS.

[Maria Ines]

Estimados Académicos y Alumnos,

Se les invita para el próximo Miércoles 28 de Diciembre a las 14:30 hrs, 
al Seminario Matemáticas Discretas, este seminario se realizará en la 
sala John Von Neumann CMM, Beauchef 851, Torre Norte, Piso 7, (ingreso 
por ascensores torre poniente, piso 7).
/*
SEMINARIO

MATEMÁTICAS DISCRETAS

EXPOSITOR
Luis Rademacher.
U. of California, Davis


TITULO:
Provably efficient high dimensional feature extraction

Abstract:*/

The goal of inference is to extract information from data. A basic 
building block in high dimensional inference is feature extraction, that 
is, to compute functionals of given data that represent it in a way that 
highlights some underlying structure. For example, Principal Component 
Analysis is an algorithm that finds a basis to represent data that 
highlights the property of data being close to a low-dimensional 
subspace. A fundamental challenge in high dimensional inference is the 
design of algorithms that are provably efficient and accurate as the 
dimension grows. In this context, I will describe two well-established 
feature extraction techniques: column subset selection (CSS) and 
independent component analysis (ICA). I will also present work by my 
coauthors and myself on CSS with optimal approximation guarantees, new 
applications of ICA and ICA for heavy-tailed distributions.

Miércoles 28 de Diciembre a las 14:30 hrs. Sala de Seminarios John Von 
Neumann CMM, Torre Norte, Piso 7.

Esperando contar con su presencia, les saluda,

Ma. Inés Rivera

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listas.dim.uchile.cl/pipermail/seminario/attachments/20161221/c3d4d1ad/attachment.html>