Symmetric Equilibrium Learning of VAEs
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00386312" target="_blank" >RIV/68407700:21230/24:00386312 - isvavai.cz</a>
Result on the web
<a href="https://proceedings.mlr.press/v238/flach24a.html" target="_blank" >https://proceedings.mlr.press/v238/flach24a.html</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Symmetric Equilibrium Learning of VAEs
Original language description
We view variational autoencoders (VAE) as decoder-encoder pairs, which map distributions in the data space to distributions in the latent space and vice versa. The standard learning approach for VAEs is the maximisation of the evidence lower bound (ELBO). It is asymmetric in that it aims at learning a latent variable model while using the encoder as an auxiliary means only. Moreover, it requires a closed form a-priori latent distribution. This limits its applicability in more complex scenarios, such as general semi-supervised learning and employing complex generative models as priors. We propose a Nash equilibrium learning approach, which is symmetric with respect to the encoder and decoder and allows learning VAEs in situations where both the data and the latent distributions are accessible only by sampling. The flexibility and simplicity of this approach allows its application to a wide range of learning scenarios and downstream tasks.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proc. of the International Conference on Artificial Intelligence and Statistics
ISBN
—
ISSN
2640-3498
e-ISSN
2640-3498
Number of pages
9
Pages from-to
3214-3222
Publisher name
Proceedings of Machine Learning Research
Place of publication
—
Event location
Valencia
Event date
May 2, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001286500302013