Frames, Reproducing Kernels, Regularization and Learning

@article{Rakotomamonjy2005FramesRK,
  title={Frames, Reproducing Kernels, Regularization and Learning},
  author={Alain Rakotomamonjy and St{\'e}phane Canu},
  journal={Journal of Machine Learning Research},
  year={2005},
  volume={6},
  pages={1485-1515}
}
This work deals with a method for building a reproducing kern el Hilbert space (RKHS) from a Hilbert space with frame elements having special propertie s. Conditions on existence and a method of construction are given. Then, these RKHS are used within t he framework of regularization theory for function approximation. Implications on semipa rametric estimation are discussed and a multiscale scheme of regularization is also proposed. Resu lts on toy and real-world approximation problems… CONTINUE READING
Highly Cited
This paper has 37 citations. REVIEW CITATIONS