[Ml-stat-talks] Fwd: CSML Seminar Series, April 25th at 12:30pm Green Hall, Room 0-S-6

Barbara Engelhardt bee at princeton.edu
Mon Apr 24 10:01:01 EDT 2017

Talk of interest tomorrow at 12:30.

---------- Forwarded message ----------

*Please join us for CSML’s Seminar on April 25**th** at 12:30 with John P.
Cunningham from Columbia University.  *

John P. Cunningham
CSML Seminar
Tuesday, April 25, 2017
Green Hall, Room 0-S-6
**Lunch will be provided**

*Title*: Structure in multi-index tensor data: a trivial byproduct of
simpler phenomena?

*Abstract*: As large tensor-variate data become increasingly common across
applied machine learning and statistics, complex analysis methods for these
data similarly increase in prevalence.  Such a trend offers the opportunity
to understand subtler and more meaningful features of the data that,
ostensibly, could not be studied with simpler datasets or simpler
methodologies.  While promising, these advances are also perilous: novel
analysis techniques do not always consider the possibility that their
results are in fact an expected consequence of some simpler, already-known
feature of simpler data.  For example, suppose one fits a time series model
(e.g. Kalman Filter or multivariate GARCH) to data indexed by time,
measurement dimension, and experimental sample.  Was a particular model fit
achieved simply because the data was temporally smooth, and/or had
correlated measurements (or samples)?  I will present two works that
address this growing problem, the first of which uses Kronecker algebra to
derive a tensor-variate maximum entropy distribution that has
user-specified moments along each mode.  This distribution forms the basis
of a statistical hypothesis test, and I will use this test to answer two
active debates in the neuroscience community over the triviality of certain
observed structure in data.  In the second part, I will discuss how to
extend this maximum entropy formulation to arbitrary constraints using deep
neural network architectures in the flavor of implicit generative modeling,
and I will use this method in a texture synthesis application.

If you would like to be added to the CSML listserv, please email:
*sjohanse at Princeton.edu* <sjohanse at Princeton.edu>

Thank you!
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/ml-stat-talks/attachments/20170424/45757f37/attachment.html>

More information about the Ml-stat-talks mailing list