Robust Large-Margin Learning in Hyperbolic Space

04/11/2020
by   Melanie Weber, et al.
12

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/01/2018

Large-Margin Classification in Hyperbolic Space

Representing data in hyperbolic space can effectively capture latent hie...
research
02/14/2023

Horocycle Decision Boundaries for Large Margin Classification in Hyperbolic Space

Hyperbolic spaces have been quite popular in the recent past for represe...
research
05/02/2023

A Quadtree for Hyperbolic Space

We propose a data structure in d-dimensional hyperbolic space that can b...
research
08/25/2023

Hyperbolic Random Forests

Hyperbolic space is becoming a popular choice for representing data due ...
research
01/12/2021

Hyperbolic Deep Neural Networks: A Survey

Recently, there has been a raising surge of momentum for deep representa...
research
03/07/2022

Provably Accurate and Scalable Linear Classifiers in Hyperbolic Spaces

Many high-dimensional practical data sets have hierarchical structures i...
research
09/08/2021

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