eCommons

 

Riemannian Geometry in Machine Learning

Other Titles

Abstract

Although machine learning researchers have introduced a plethora of useful constructions for learning over Euclidean space, numerous types of data found in various applications areas benefit from, if not necessitate, a non-Euclidean treatment. In this thesis I cover the need for Riemannian geometric constructs to (1) build more principled generalizations of common Euclidean operations used in geometric machine learning models as well as to (2) enable general manifold density learning in contexts that require it. Said contexts include theoretical physics, robotics, and computational biology. I will cover two of my papers that fit into (1) above, namely the ICML 2020 paper "Differentiating through the Fréchet Mean" as well as the ICML 2022 workshop paper "Riemannian Residual Neural Networks", presented at the second annual "Topology, Algebra, and Geometry in Machine Learning" workshop. I will also cover two of my papers that fit into (2) above, namely the NeurIPS 2020 paper "Neural Manifold Ordinary Differential Equations" and the NeurIPS 2021 paper "Equivariant Manifold Flows." Finally, I will briefly discuss the implications of the work done as well as potential directions for future work.

Journal / Series

Volume & Issue

Description

224 pages

Sponsorship

Date Issued

2022-08

Publisher

Keywords

geometric deep learning; machine learning; riemannian geometry

Location

Effective Date

Expiration Date

Sector

Employer

Union

Union Local

NAICS

Number of Workers

Committee Chair

De Sa, Christopher Matthew

Committee Co-Chair

Committee Member

West, James Edward

Degree Discipline

Computer Science

Degree Name

M.S., Computer Science

Degree Level

Master of Science

Related Version

Related DOI

Related To

Related Part

Based on Related Item

Has Other Format(s)

Part of Related Item

Related To

Related Publication(s)

Link(s) to Related Publication(s)

References

Link(s) to Reference(s)

Previously Published As

Government Document

ISBN

ISMN

ISSN

Other Identifiers

Rights

Rights URI

Types

dissertation or thesis

Accessibility Feature

Accessibility Hazard

Accessibility Summary

Link(s) to Catalog Record