A Theory of Hyperbolic Prototype Learning

10/15/2020
by   Martin Keller-Ressel, et al.
0

We introduce Hyperbolic Prototype Learning, a type of supervised learning, where class labels are represented by ideal points (points at infinity) in hyperbolic space. Learning is achieved by minimizing the 'penalized Busemann loss', a new loss function based on the Busemann function of hyperbolic geometry. We discuss several theoretical features of this setup. In particular, Hyperbolic Prototype Learning becomes equivalent to logistic regression in the one-dimensional case.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset