Generalization Bounds for K-Dimensional Coding Schemes in Hilbert Spaces

@inproceedings{Maurer2008GeneralizationBF,
  title={Generalization Bounds for K-Dimensional Coding Schemes in Hilbert Spaces},
  author={Andreas Maurer and Massimiliano Pontil},
  booktitle={ALT},
  year={2008}
}
We give a bound on the expected reconstruction error for a general coding method where data in a Hilbert space are represented by finite dimensional coding vectors. The result can be specialized to Kmeans clustering, nonnegative matrix factorization and the sparse coding techniques introduced by Olshausen and Field.