PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Generalization Bounds for K-Dimensional Coding Schemes in Hilbert Spaces
Andreas Maurer and Massimiliano Pontil
In: Algorithmic Learning Theory 2008, 13-16 Oct 2008, Budapest.


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 K-means clustering, nonnegative matrix factorization and the sparse coding techniques introduced by Olshausen and Field.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:5357
Deposited By:Massimiliano Pontil
Deposited On:24 March 2009