Dimensionality-Dependent Generalization Bounds for <i>k</i>-Dimensional Coding Schemes
Dimensionality-Dependent Generalization Bounds for <i>k</i>-Dimensional Coding Schemes
The k-dimensional coding schemes refer to a collection of methods that attempt to represent data using a set of representative k-dimensional vectors and include nonnegative matrix factorization, dictionary learning, sparse coding, k-means clustering, and vector quantization as special cases. Previous generalization bounds for the reconstruction error of the k-dimensional coding …