Activity Number:
|
406
|
Type:
|
Invited
|
Date/Time:
|
Tuesday, August 2, 2016 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Section on Statistical Learning and Data Science
|
Abstract #318490
|
View Presentation
|
Title:
|
Convex Regularization for High-Dimensional Tensor Regression
|
Author(s):
|
Ming Yuan* and Garvesh Raskutti
|
Companies:
|
University of Wisconsin and University of Wisconsin - Madison
|
Keywords:
|
Tensor Regression
|
Abstract:
|
We present a general convex optimization approach for solving high-dimensional tensor regression problems under general low-dimensional structural assumptions. We consider using convex and weakly decomposable regularizers assuming the underlying tensor lies in an unknown low-dimensional subspace. Within this general framework, we derive upper bounds for convex methods applied to tensor regression for general dependent Gaussian design. Our framework provides rates of convergence for a number of fundamental statistical models of interests.
|
Authors who are presenting talks have a * after their name.