[Colloquium] REMINDER: Talks at TTIC: Min Xu, CMU

[Dawn Ellis]

When:     Wednesday, March 4th at 11am

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

Who:       Min Xu, CMU

Title:       Faithful Variable Screening for High-Dimensional Convex
Regression

We study the problem of variable selection in convex nonparametric
regression. Under the assumption that the true regression function is
convex and that the underlying density satisfies a mild boundary condition,
we prove that it is faithful to use an addition approximation, in the sense
that the approximation introduces no false negatives. Based on this result,
we develop a screening procedure to select a subset of variables that
contains the relevant variables. Our approach is a two-stage quadratic
programming method that estimates a sum of one-dimensional convex
functions, followed by one-dimensional concave regression fits on the
residuals. In contrast to previous methods for sparse additive models, the
optimization is finite dimensional and requires no tuning parameters for
smoothness. We give a finite sample statistical analysis, and introduce
algorithms for efficiently carrying out the required quadratic programs.
The approach often yields exact variable selection in experiments, and
leads to computational and statistical advantages over fitting a full
model, and provides an effective, practical approach to variable screening
in convex regression.

Host:  Nati Srebro, nati at ttic.edu



-- 
*Dawn Ellis*
Administrative Coordinator,
Bookkeeper
773-834-1757
dellis at ttic.edu

TTIC
6045 S. Kenwood Ave.
Chicago, IL. 60637
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20150303/24dcff5e/attachment-0001.htm