Non-linear Embeddings in Hilbert Simplex Geometry

03/22/2022
by   Frank Nielsen, et al.
0

A key technique of machine learning and computer vision is to embed discrete weighted graphs into continuous spaces for further downstream processing. Embedding discrete hierarchical structures in hyperbolic geometry has proven very successful since it was shown that any weighted tree can be embedded in that geometry with arbitrary low distortion. Various optimization methods for hyperbolic embeddings based on common models of hyperbolic geometry have been studied. In this paper, we consider Hilbert geometry for the standard simplex which is isometric to a vector space equipped with the variation polytope norm. We study the representation power of this Hilbert simplex geometry by embedding distance matrices of graphs. Our findings demonstrate that Hilbert simplex geometry is competitive to alternative geometries such as the Poincaré hyperbolic ball or the Euclidean geometry for embedding tasks while being fast and numerically robust.

READ FULL TEXT

page 5

page 8

research
04/17/2020

Hilbert geometry of the Siegel disk: The Siegel-Klein disk model

We study the Hilbert geometry induced by the Siegel disk domain, an open...
research
12/13/2021

A cognitively driven weighted-entropy model for embedding semantic categories in hyperbolic geometry

In this paper, an unsupervised and cognitively driven weighted-entropy m...
research
05/18/2020

Hyperbolic Distance Matrices

Hyperbolic space is a natural setting for mining and visualizing data wi...
research
04/21/2023

Hyperbolic Geometry in Computer Vision: A Survey

Hyperbolic geometry, a Riemannian manifold endowed with constant section...
research
10/08/2019

Beyond Vector Spaces: Compact Data Representationas Differentiable Weighted Graphs

Learning useful representations is a key ingredient to the success of mo...
research
10/01/2020

From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering

Similarity-based Hierarchical Clustering (HC) is a classical unsupervise...
research
11/16/2019

Where are the Natural Numbers in Hilbert's Foundations of Geometry?

Hilbert's Foundations of Geometry was perhaps one of the most influentia...

Please sign up or login with your details

Forgot password? Click here to reset