Trace Norm Regularization: Theory, Algorithms, and Applications¶
Professor Jieping Ye
Department of Computer Science and Engineering
Arizona State University
Abstract :
The minimization of a smooth loss function regularized by the trace norm of the matrix variable has applications in many machine learning tasks including multi-task learning and matrix completion. The standard semidefinite programming formulation for this problem is computationally expensive. In this talk, I will present efficient algorithms for the trace norm regularization by exploiting the special structure of the trace norm. In addition, I will discuss the performance bounds of the least squares regression with trace norm regularization.
Finally, I will introduce the SLEP package recently developed in my group for large-sale sparse learning.
Bio:
Jieping Ye is an Associate Professor of the Department of Computer Science and Engineering at Arizona State University. He received his Ph.D. in Computer Science from University of Minnesota, Twin Cities in 2005. His research interests include machine learning, data mining, and biomedical informatics. He won the outstanding student paper award at ICML in 2004, the SCI Young Investigator of the Year Award at ASU in 2007, the SCI Researcher of the Year Award at ASU in 2009, and the NSF CAREER Award in 2010.