Citation
Dorsa Sadigh, Henrik Ohlsson, S. Shankar Sastry, Sanjit Seshia. "Robust Subspace System Identification via Weighted Nuclear Norm Optimization". 19th World Congress of the International Federation of Automatic Control (IFAC), 24, August, 2014.

Abstract
Subspace identication is a classical and very well studied problem in system identication. The problem was recently posed as a convex optimization problem via the nuclear norm relaxation. Inspired by robust PCA, we extend this framework to handle outliers. The proposed framework takes the form of a convex optimization problem with an objective that trades o t, rank and sparsity. As in robust PCA, it can be problematic to nd a suitable regularization parameter.We show how the space in which a suitable parameter should be sought can be limited to a bounded open set of the two-dimensional parameter space. In practice,

Electronic downloads

• https://www.src.org/library/publication/p069783/. (Link to paper on SRC website.)
• http://arxiv.org/pdf/1312.2132v1.pdf
• http://escholarship.org/uc/item/9d5005m3. (Link to eScholarship site)
• http://people.eecs.berkeley.edu/~sseshia/pubdir/ifac14.pdf. (Link to "camera ready" version)

• HTML

  Dorsa Sadigh, Henrik Ohlsson, S. Shankar Sastry, Sanjit
  Seshia. <a
  href="http://www.terraswarm.org/pubs/292.html"
  >Robust Subspace System Identification via Weighted
  Nuclear Norm Optimization</a>, 19th World Congress of
  the International Federation of Automatic Control (IFAC),
  24, August, 2014.

• Plain text

  Dorsa Sadigh, Henrik Ohlsson, S. Shankar Sastry, Sanjit
  Seshia. "Robust Subspace System Identification via
  Weighted Nuclear Norm Optimization". 19th World
  Congress of the International Federation of Automatic
  Control (IFAC), 24, August, 2014.

• BibTeX

  @inproceedings{SadighOhlssonSastrySeshia14_RobustSubspaceSystemIdentificationViaWeightedNuclear,
      author = {Dorsa Sadigh and Henrik Ohlsson and S. Shankar
                Sastry and Sanjit Seshia},
      title = {Robust Subspace System Identification via Weighted
                Nuclear Norm Optimization},
      booktitle = {19th World Congress of the International
                Federation of Automatic Control (IFAC)},
      day = {24},
      month = {August},
      year = {2014},
      abstract = {Subspace identication is a classical and very
                well studied problem in system identication. The
                problem was recently posed as a convex
                optimization problem via the nuclear norm
                relaxation. Inspired by robust PCA, we extend this
                framework to handle outliers. The proposed
                framework takes the form of a convex optimization
                problem with an objective that trades o t, rank
                and sparsity. As in robust PCA, it can be
                problematic to nd a suitable regularization
                parameter.We show how the space in which a
                suitable parameter should be sought can be limited
                to a bounded open set of the two-dimensional
                parameter space. In practice,},
      URL = {http://terraswarm.org/pubs/292.html}
  }
  

Posted by Barb Hoversten on 31 Mar 2014.
Groups: tools