Learning with Spectral Kernels and Heavy-Tailed Data

Details Learning with Spectral Kernels and Heavy-Tailed Data Learning with Spectral Kernels and Heavy-Tailed Data

2009-06-24

arxiv.org/abs/0906.4539v2

Computer Science

Learning

21 pages. Substantially revised and extended relative to the first version

Scientific paper

Two ubiquitous aspects of large-scale data analysis are that the data often have heavy-tailed properties and that diffusion-based or spectral-based methods are often used to identify and extract structure of interest. Perhaps surprisingly, popular distribution-independent methods such as those based on the VC dimension fail to provide nontrivial results for even simple learning problems such as binary classification in these two settings. In this paper, we develop distribution-dependent learning methods that can be used to provide dimension-independent sample complexity bounds for the binary classification problem in these two popular settings. In particular, we provide bounds on the sample complexity of maximum margin classifiers when the magnitude of the entries in the feature vector decays according to a power law and also when learning is performed with the so-called Diffusion Maps kernel. Both of these results rely on bounding the annealed entropy of gap-tolerant classifiers in a Hilbert space. We provide such a bound, and we demonstrate that our proof technique generalizes to the case when the margin is measured with respect to more general Banach space norms. The latter result is of potential interest in cases where modeling the relationship between data elements as a dot product in a Hilbert space is too restrictive.

Affiliated with

Also associated with

No associations

Rating

Learning with Spectral Kernels and Heavy-Tailed Data does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Learning with Spectral Kernels and Heavy-Tailed Data, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning with Spectral Kernels and Heavy-Tailed Data will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-106577