[Statlist] Next talk: Friday, September 16, 2016 with Venkat Chandrasekaran, California Institute of Technology, USA

[Maurer Letizia]

E-mail from the  Statlist using stat.ch<mailto:Statlist using stat.ch>  mailing list
_________________________________________________
ETH and University of Zurich

Organisers:
Proff. P. Bühlmann - L. Held - T. Hothorn - M. Maathuis -
N. Meinshausen - S. van de Geer - M. Wolf

****************************************************************

We are glad to announce the following talk:

Friday, September 16, 2016 at 15.15h  ETH Zurich HG G 19.1
with Venkat Chandrasekaran, California Institute of Technology, USA
********************************************************************************

Title:
Learning Semidefinite Regularizers via Matrix Factorization<https://www.math.ethz.ch/sfs/news-and-events/research-seminar.html?s=hs16#e_9127>

Abstract:

Regularization techniques are widely employed in the solution of inverse problems in data analysis and scientific computing due to their effectiveness in addressing difficulties due to ill-posedness. In their most common manifestation, these methods take the form of penalty functions added to the objective in optimization-based approaches for solving inverse problems. The purpose of the penalty function is to induce a desired structure in the solution, and these functions are specified based on prior domain-specific expertise. We consider the problem of learning suitable regularization functions from data in settings in which prior domain knowledge is not directly available. Previous work under the title of 'dictionary learning' or 'sparse coding' may be viewed as learning a polyhedral regularizer from data. We describe generalizations of these methods to learn semidefinite regularizers by computing structured factorizations of data matrices. Our algorithmic approach for computing these factorizations combines recent techniques for rank minimization problems along with operator analogs of Sinkhorn scaling. The regularizers obtained using our framework can be employed effectively in semidefinite programming relaxations for solving inverse problems. (Joint work with Yong Sheng Soh)

	[[alternative HTML version deleted]]