[Colloquium] TTIC Talks: Alex Agarwal, UC Berkeley

[Liv Leader]

When:     Monday, March 19 @ 11 a.m.

Where:    TTIC, 6045 S. Kenwood Avenue, Room #526

Who:       Alex Agarwal, UC Berkeley

Title:       Statistics meets Computation: Exploiting structure for
efficient learning with large data-sets

The past decade has seen the emergence of datasets of an unprecedented
scale, with both large sample sizes and dimensionality. Massive data
sets arise in various domains, among them computer vision, natural
language processing, computational biology, social networks analysis
and recommendation systems, to name a few.  In many such problems, the
bottleneck is not just the number of data samples, but also the
computational resources available to process the data.  An important goal
in such problems is to understand how we might leverage the
statistical structure of the problem to get efficient computational procedures.

In this talk, I present two research threads that provide
different lines of attack on this broader research agenda: (i)
distributed algorithms for statistical inference; and (ii) interplay between
statistical and computational complexities in structured high-dimensional
estimation. In both the examples, we will demonstrate how we can beat
the worst-case
complexity of the computational problem by exploiting the statistical
structure.

[Joint work with John Duchi, Sahand Negahban, Peter Bartlett and
Martin Wainwright]

Host: Nati Srebro, nati at ttic.edu

-- 
Liv Leader
Human Resources Coordinator

Toyota Technological Institute Chicago
6045 S Kenwood Ave
Chicago, IL 60637
Phone- (773) 702-5033
Fax-     (773) 834-9881
Email-  lleader at ttic.edu
Web-   www.ttic.edu