IPAM Institute for Pure and Applied Mathematics UCLA NSF
Skip Navigation Links
Main Page
Program Poster PDF
Lodging & Air Travel
Schedule and Presentations

Structure and Randomness in System Identification and Learning

January 15 - 18, 2013


Organizing Committee | Scientific Overview | Speaker List

Application/Registration | Contact Us

Organizing Committee

Maryam Fazel (University of Washington, Electrical Engineering)
Mehran Mesbahi (University of Washington, Aeronautics and Astronautics)
Nathan Srebro (University of Chicago, Computer Science, Toyota Technological Institute)
Lieven Vandenberghe (University of California, Los Angeles (UCLA), EE)

Back to Top

Scientific Overview

Machine learning and system identification communities are faced with similar problems where one needs to construct a model from limited or noisy observations. The challenge lies in solving an ill-posed inverse problem, where the number of available measurements is much smaller than the dimension of the model to be estimated. However, typically two ingredients, (i) simple model structures and (ii) random observations, go hand in hand to allow learning or recovery guarantees.

For example, in applications, model complexity can be expressed as the cardinality of a vector, the rank of a matrix or tensor, or more generally, the number of simple units or "atoms" needed to build a model consistent with the observations. This general notion of complexity covers recently studied problems in compressed sensing, low-rank matrix and tensor recovery, matrix completion, recovering low-rank structures corrupted by outliers, and sparse graphical models. Considering time-dynamics requires notions of (temporal) model structure such as the McMillan degree (the order of the minimal realization) of a linear system representing given input-output observations.

Exploiting the structure in a system often leads to significant computational efficiency, and the workshop will also examine the role of structured convex optimization.

This workshop will bring together researchers from machine learning and control theory, as well as high dimensional statistics and convex optimization, to explore this research area.

The workshop will also include a poster session; a request for posters will be sent to registered participants in advance of the workshop.

Back to Top

Confirmed Speakers

Alekh Agarwal (Microsoft Research)
Emmanuel Candes (Stanford University)
Constantine Caramanis (University of Texas at Austin)
Venkat Chandrasekaran (California Institute of Technology)
Munther Dahleh (Massachusetts Institute of Technology)
Inderjit Dhillon (University of Texas at Austin)
John Doyle (California Institute of Technology)
Maryam Fazel (University of Washington)
Babak Hassibi (California Institute of Technology)
Lennart Ljung (Linköping University)
Michael Mahoney (Stanford University)
Andrea Montanari (Stanford University)
Deanna Needell (Claremont McKenna College)
Sahand Negahban (Massachusetts Institute of Technology)
Pablo Parrilo (Massachusetts Institute of Technology)
Nathan Srebro (University of Chicago)
Mario Sznaier (Northeastern University)
Joel Tropp (California Institute of Technology)
Stephen Wright (University of Wisconsin-Madison)
Lin Xiao (Microsoft Research)
Tong Zhang (Rutgers University-Camden)

Back to Top

Back to Top

Contact Us:

Institute for Pure and Applied Mathematics (IPAM)
Attn: SI2013
460 Portola Plaza
Los Angeles CA 90095-7121
Phone: 310 825-4755
Fax: 310 825-4756
Email: ipam@ucla.edu
Website: http://www.ipam.ucla.edu/programs/si2013/

Back to Top

NSF Math Institutes   |   Webmaster