Back to search

University of Kent

A study of representation learning without encoders

Abstract

dc:description.abstract

Latent variables models have long been used in dimensionality reduction and representation learning. By far, the most common method is based on the Autoencoder, which is formed by an encoder-decoder pair. Recently, a model was introduced called the Gradient Origin Network (GON) which replaces the encoder with a gradient descent step. While being shown to be similarly performant, not much else is known about how it reaches representations. This work extends known results applicable to autoencoders such as its convergence to PCA solutions, while trying to establish representational similarity. As GONs have a variational allegory, we establish the presence of posterior collapse and a polarised regime in variational GONs (VGONs). Finally, we extend the definition of the polarised regime to better encapsulate a wider variety of models beyond just variational models based on a Gaussian prior.

Degree

thesis:*
Name dc:type.qualificationname
phd
Level dc:type.qualificationlevel
doctoral
Grantor dc:publisher.institution
University of Kent
Year dc:date.issued
2026

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Clapham, Peter
Advisor dc:contributor.advisor
  • Grzes, Marek

Subjects

dc:subject × 1

Rights

Language dc:language
en

Chain of custody

source
Harvested from
University of Kent
Base URL
kar.kent.ac.uk/cgi/oai2
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Clapham, Peter. A study of representation learning without encoders. doctoral thesis, University of Kent, 2026.