Robust Large-Margin Learning in Hyperbolic Space

by   Melanie Weber, et al.

Recently, there has been a surge of interest in representation learning in hyperbolic spaces, driven by their ability to represent hierarchical data with significantly fewer dimensions than standard Euclidean spaces. However, the viability and benefits of hyperbolic spaces for downstream machine learning tasks have received less attention. In this paper, we present, to our knowledge, the first theoretical guarantees for learning a classifier in hyperbolic rather than Euclidean space. Specifically, we consider the problem of learning a large-margin classifier for data possessing a hierarchical structure. Our first contribution is a hyperbolic perceptron algorithm, which provably converges to a separating hyperplane. We then provide an algorithm to efficiently learn a large-margin hyperplane, relying on the careful injection of adversarial examples. Finally, we prove that for hierarchical data that embeds well into hyperbolic space, the low embedding dimension ensures superior guarantees when learning the classifier directly in hyperbolic space.


page 1

page 2

page 3

page 4


Large-Margin Classification in Hyperbolic Space

Representing data in hyperbolic space can effectively capture latent hie...

Horocycle Decision Boundaries for Large Margin Classification in Hyperbolic Space

Hyperbolic spaces have been quite popular in the recent past for represe...

A Quadtree for Hyperbolic Space

We propose a data structure in d-dimensional hyperbolic space that can b...

Hyperbolic Random Forests

Hyperbolic space is becoming a popular choice for representing data due ...

Hyperbolic Deep Neural Networks: A Survey

Recently, there has been a raising surge of momentum for deep representa...

Provably Accurate and Scalable Linear Classifiers in Hyperbolic Spaces

Many high-dimensional practical data sets have hierarchical structures i...

Highly Scalable and Provably Accurate Classification in Poincare Balls

Many high-dimensional and large-volume data sets of practical relevance ...

Please sign up or login with your details

Forgot password? Click here to reset