Grzes, Marek, Bonheme, Lisa (2023) The Polarised Regime of identifiable Variational Autoencoders. In: The First Tiny Papers Track at the International Conference on Learning Representations (ICLR). . (KAR id:101233)
|
PDF
Publisher pdf
Language: English |
|
|
Download this file (PDF/445kB) |
Preview |
| Request a format suitable for use with assistive technology e.g. a screenreader | |
| Official URL: https://openreview.net/pdf?id=iSkcAjBqUHU |
|
Abstract
The polarised regime of VAEs gives them a signature behaviour with specific strengths and weaknesses which are well-studied (Dai et al., 2017; Rolinek et al., 2019; Dai et al., 2020; Bonheme & Grzes, 2021). In this paper, we show that iVAEs also behave in a polarised regime and are thus likely to exhibit the same behaviour.
| Item Type: | Conference or workshop item (Paper) |
|---|---|
| Subjects: | Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming, > QA76.87 Neural computers, neural networks |
| Divisions: | Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing |
| Depositing User: | Marek Grzes |
| Date Deposited: | 11 May 2023 13:26 UTC |
| Last Modified: | 11 May 2023 13:26 UTC |
| Resource URI: | https://kar.kent.ac.uk/id/eprint/101233 (The current URI for this page, for reference purposes) |
University of Kent Author Information
Grzes, Marek.
| Creator's ORCID: |
 https://orcid.org/0000-0003-4901-1539
|
|---|---|
| CReDIT Contributor Roles: |
Bonheme, Lisa.
| Creator's ORCID: | |
|---|---|
| CReDIT Contributor Roles: |
- Link to SensusAccess
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):
Download Statistics
Download Statistics
