Generalized Thresholding Sparsity-Aware Online Learning in a Union of Subspaces

@article{Kopsinis2011GeneralizedTS,
  title={Generalized Thresholding Sparsity-Aware Online Learning in a Union of Subspaces},
  author={Yannis Kopsinis and Konstantinos Slavakis and Sergios Theodoridis and Stephen McLaughlin},
  journal={CoRR},
  year={2011},
  volume={abs/1112.0665}
}
This paper studies a non-convexly constrained, sparse inve rse problem in time-varying environments from a set theoret ic estimation perspective. A new theory is developed that allo ws for the incorporation, in a unifying way, of different thr esholding rules to promote sparsity, that may be even related to non-co nvex penalty functions. The resulted generalized threshol ding operator is embodied in an efficient online, sparsity-aware learning scheme. The algorithm is of low computational… CONTINUE READING

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 53 REFERENCES

Fast sparse regression and classificat ion

  • J. H. Friedman
  • Dept. of Statistics, Stanford University, Tech…
  • 2008
Highly Influential
4 Excerpts

Adaptive projected subgradien t method for asymptotic minimization of sequence of nonnega tive convex functions,”Numerical Functional Analysis and Optimization

  • I. Yamada, N. Ogura
  • 2004
Highly Influential
5 Excerpts

Similar Papers

Loading similar papers…