[Colloquium] REMINDER: 4/27 Talks at TTIC: Gautam Dasarathy, CMU

[Mary Marre]

When:     Wednesday, April 27th at 11:00 am

Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526

Who:      Gautam Dasarathy, CMU


Title: Learning Large Graphs from Compressed and Subsampled Data

Abstract:  Many machine learning and statistical inference tasks involve
estimating graphical representations of correlations or dependencies in
data.  However, in various naturally arising scenarios, it can be expensive
or impossible to obtain joint measurements of all the involved variables.
For example, collecting simultaneous measurements from a large network of
sensors may require a prohibitive level of communication and coordination
and building a protein-protein interaction network may need a prohibitive
number of pairwise correlation tests.In this talk, I will describe my
research agenda motivated by this important consideration, focusing in
particular on two approaches that instantiate it.
In the first part, I will describe a framework for learning covariance (or,
dependence) graphs from compressed data. Specifically, I will outline a
procedure for learning the covariance structure by first grouping the
underlying variables and measuring interactions (or correlations) at this
grouped level. By drawing connections between high-dimensional convex
geometry and novel combinatorial properties of certain random graphs, I
will demonstrate that this procedure is both computationally efficient and
statistically consistent while requiring considerably fewer number of
pairwise correlations.

In the second part, I will describe a new framework for learning a
graphical model (i.e., a conditional independence graph) by sequentially
and interactively subsampling the data. The algorithms proposed adapt to
the structure of the unknown graph and focus attention on its denser
regions. Both theory and experiments show that such algorithms
significantly outperform their classical counterparts in terms of the total
measurement resources needed.

I will conclude by sketching a roadmap for future research in statistical
model selection (and more generally, data analysis) while taking into
account such natural constraints on the measurement process.

http://gautamdasarathy.com


Host: Nathan Srebro, nati at ttic.edu




Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 504*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20160426/795b382c/attachment.htm