On-line Nonlinear Sparse Approximation of Functions

@article{Honeine2007OnlineNS,
  title={On-line Nonlinear Sparse Approximation of Functions},
  author={Paul Honeine and C{\'e}dric Richard and Jos{\'e} Carlos Moreira Bermudez},
  journal={2007 IEEE International Symposium on Information Theory},
  year={2007},
  pages={956-960}
}
This paper provides new insights into on-line nonlinear sparse approximation of functions based on the coherence criterion. We revisit previous work, and propose tighter bounds on the approximation error based on the coherence criterion. Moreover, we study the connections between the coherence criterion and both the approximate linear dependence criterion and the principal component analysis. Finally, we derive a kernel normalized LMS algorithm based on the coherence criterion, which has linear… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 33 CITATIONS

Analyzing Sparse Dictionaries for Online Learning With Kernels

  • IEEE Transactions on Signal Processing
  • 2014
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS

Fixed-budget kernel least mean squares

  • Proceedings of 2012 IEEE 17th International Conference on Emerging Technologies & Factory Automation (ETFA 2012)
  • 2012
VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Kernel Least Mean $p$-Power Algorithm

  • IEEE Signal Processing Letters
  • 2017
VIEW 1 EXCERPT
CITES METHODS

Approximation Errors of Online Sparsification Criteria

  • IEEE Transactions on Signal Processing
  • 2015
VIEW 3 EXCERPTS
CITES BACKGROUND

Convex combinations of kernel adaptive filters

  • 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)
  • 2014
VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 12 REFERENCES

Nonlinear kernelbased adaptive filtering with order controlled by a coherence criterion

C. Richard, J.C.M. Bermudez, P. Honeine
  • submitted to IEEE Transactions on Signal Processing, 2007.
  • 2007
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

The kernel recursive least-squares algorithm

  • IEEE Transactions on Signal Processing
  • 2004
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Eigenspace methods and subset selection in kernel based learning

L. Hoegaerts
  • PhD thesis, Faculty of Engineering, K.U.Leuven, Leuven, Belgium, Jun. 2005.
  • 2005
VIEW 1 EXCERPT

Greed is good: algorithmic results for sparse approximation

  • IEEE Transactions on Information Theory
  • 2004
VIEW 3 EXCERPTS

Sparse representations in unions of bases

  • IEEE Trans. Information Theory
  • 2003
VIEW 1 EXCERPT