Learning Low-Density Separators

Details Learning Low-Density Separators Learning Low-Density Separators

2008-05-19

arxiv.org/abs/0805.2891v2

Computer Science

Learning

15 pages, 1 figure

Scientific paper

We define a novel, basic, unsupervised learning problem - learning the lowest density homogeneous hyperplane separator of an unknown probability distribution. This task is relevant to several problems in machine learning, such as semi-supervised learning and clustering stability. We investigate the question of existence of a universally consistent algorithm for this problem. We propose two natural learning paradigms and prove that, on input unlabeled random samples generated by any member of a rich family of distributions, they are guaranteed to converge to the optimal separator for that distribution. We complement this result by showing that no learning algorithm for our task can achieve uniform learning rates (that are independent of the data generating distribution).

Affiliated with

Also associated with

No associations

Rating

Learning Low-Density Separators 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 Low-Density Separators, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning Low-Density Separators will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-648411