Generalization Bounds for Subspace Selection and Hyperbolic PCA

Andreas MaurerSLSFS 2005 · OpenReview

Abstract

We present a method which uses example pairs of equal or unequal class labels to select a subspace with near optimal metric properties in a kernel-induced Hilbert space. A representation of finite dimensional projections as bounded linear functionals on a space of Hilbert-Schmidt operators leads to PAC-type performance guarantees for the resulting feature maps. The proposed algorithm returns the projection onto the span of the principal eigenvectors of an empirical operator constructed in terms of the example pairs. It can be applied to meta-learning environments and experiments demonstrate an effective transfer of knowledge between different but related learning tasks.
BibTeX
@inproceedings{maurer2005generalization,
  author = {Andreas Maurer},
  title = {{Generalization Bounds for Subspace Selection and Hyperbolic PCA}},
  booktitle = {SLSFS},
  year = {2005},
  url = {https://openreview.net/forum?id=bOzZMTUbg-a},
}

Loading related content...

Figure