[Colloquium] TTIC Colloquium: Shaowei Lin, UC Berkeley
Liv Leader
lleader at ttic.edu
Fri Nov 4 09:43:08 CDT 2011
When: Monday, November 7 @ 11 a.m.
Where: TTIC Conference Room #526, 6045 S. Kenwood Avenue, 5th Floor
Who: Shaowei Lin, UC Berkeley
Title: What is Singular Learning Theory?
Abstract: Singular models occur frequently in machine learning and
computational biology. In this talk, we give a basic introduction to
Sumio Watanabe's Singular Learning Theory, as outlined in his book
"Algebraic Geometry and Statistical Learning Theory". Watanabe's key
insight to studying singular models was to use a deep result in
algebraic geometry known as Hironaka's Resolution of Singularities.
This result allows him to reparametrize the model in a normal form so
that central limit theorems can be applied. In the second half of the
talk, we discuss new algebraic methods where we define fiber ideals
for discrete/Gaussian models which are singular. We show how to
approximate marginal likelihood integrals for these models using
Newton polyhedra.
http://math.berkeley.edu/~shaowei/
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
More information about the Colloquium
mailing list