Learning Low-Density Separators

8 years 2 months ago
Learning Low-Density Separators
Abstract. We define a novel, basic, unsupervised learning problem learning the 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).
Shai Ben-David, Tyler Lu, Dávid Pál,
Added 09 Dec 2010
Updated 09 Dec 2010
Type Journal
Year 2008
Where CORR
Authors Shai Ben-David, Tyler Lu, Dávid Pál, Miroslava Sotáková
Comments (0)