[Ml-stat-talks] ORFE Seminar tomorrow at 4:30

Philippe Rigollet rigollet at Princeton.EDU
Wed Feb 6 16:56:48 EST 2013


=== ORFE Seminar Announcement ===

DATE:   Thursday, February 7, 2013

TIME:   4:30pm

LOCATION:   Room 101, Sherrerd Hall

SPEAKER:  Gillian Chin, Northwestern University

TITLE:   Algorithms for Large Scale Convex Optimization with Applications to Machine Learning

ABSTRACT:
In this talk, we will explore the development of efficient batch optimization algorithms for
solving large scale statistical learning applications; particularly those that can be formulated as
convex, nonlinear optimization problems. We first investigate smooth unconstrained problems,
where we will introduce two effective strategies for reducing the computational cost of the
optimization process: stochastic Hessian information and dynamic gradient sampling. We will
then focus on developing second order methods for non‐smooth optimization problems,
specifically in devising a semi‐smooth Newton framework that can be used to generate several
well-known methods for machine learning. We will illustrate with applications in speech
recognition and sparse inverse covariance estimation that we have achieved improved accuracy
over existing methodologies.

--
Philippe Rigollet
www.princeton.edu/~rigollet<http://www.princeton.edu/~rigollet>





-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/ml-stat-talks/attachments/20130206/9026c1c5/attachment.html>


More information about the Ml-stat-talks mailing list