Segmentation of ARX-models using sum-of-norms regularization

  title={Segmentation of ARX-models using sum-of-norms regularization},
  author={Henrik Ohlsson and Lennart Ljung and Stephen P. Boyd},
Segmentation of time-varying systems and signals into models whose parameters are piecewise constant in time is an important and well studied problem. It is here formulated as a least-squares problem with sum-of-norms regularization over the state parameter jumps, a generalization of `1-regularization. A nice property of the suggested formulation is that it only has one tuning parameter, the regularization constant which is used to trade off fit and the number of segments. 
Highly Cited
This paper has 136 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.


Publications citing this paper.
Showing 1-10 of 80 extracted citations

136 Citations

Citations per Year
Semantic Scholar estimates that this publication has 136 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 30 references

Segmentation of ARX - models using sum - of - norms regularization

  • Y. Lin
  • 2010

CVX: Matlab Software for Disciplined

  • M. Grant, Stephen Boyd, Y. Ye
  • Convex Programming,
  • 2009
1 Excerpt

Graph implementations for nonsmooth convex programs

  • M. Grant, Stephen Boyd
  • Recent Advances in Learning and Control,
  • 2008
1 Excerpt

The System Identification Toolbox: The Manual

  • Lennart Ljung
  • The MathWorks Inc. 1st edition 1986,
  • 2007
6 Excerpts

Similar Papers

Loading similar papers…