[Ml-stat-talks] Fwd: [ORFE-Seminars] ORFE Colloquium: Robert Freund, Today at 4:30pm, Sherrerd Hall 101

Barbara Engelhardt bee at princeton.edu
Tue Apr 19 12:42:41 EDT 2016


Talk of interest.

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


=== ORFE Colloquium Announcement ===

DATE:   Today, April 19, 2016

TIME:   4:30pm

LOCATION:   Sherrerd Hall, room 101

SPEAKER:  Robert Freund, MIT

TITLE:   A New Perspective on Boosting in Linear Regression via Subgradient
Optimization and Relatives

ABSTRACT:   We analyze boosting algorithms in linear regression from the
perspective modern first-order methods in convex optimization. We show that
classic boosting algorithms in linear regression, namely the incremental
forward stagewise algorithm (FSe) and least squares boosting (LS-Boost-e),
can be viewed as subgradient descent to minimize the maximum absolute
correlation between features and residuals. We also propose a modification
of FSe that yields an algorithm for the LASSO, and that computes the LASSO
path. We derive novel comprehensive computational guarantees for all of
these boosting algorithms, which provide, for the first time, a precise
theoretical description of the amount of data-fidelity and regularization
imparted by running a boosting algorithm with a pre-specified learning rate
for a fixed but arbitrary number of iterations, for any dataset.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/ml-stat-talks/attachments/20160419/655db753/attachment.html>


More information about the Ml-stat-talks mailing list