A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
ControlVAE: Tuning, Analytical Properties, and Performance Analysis
[article]
2020
arXiv
pre-print
This paper reviews the novel concept of controllable variational autoencoder (ControlVAE), discusses its parameter tuning to meet application needs, derives its key analytic properties, and offers useful ...
In order to improve the ELBO over the regular VAE, we provide simplified theoretical analysis to inform setting the set point of KL-divergence for ControlVAE. ...
-09-2-0053 and W911NF-17-2-0196. ...
arXiv:2011.01754v1
fatcat:5opz4icb2vakhhinrkmpq7ofxq
DynamicVAE: Decoupling Reconstruction Error and Disentangled Representation Learning
[article]
2020
arXiv
pre-print
To mitigate this problem, a ControlVAE has recently been developed that dynamically tunes the KL-divergence weight in an attempt to control the trade-off to more a favorable point. ...
However, ControlVAE fails to eliminate the conflict between the need for a large β (for disentanglement) and the need for a small β. ...
RESULTS AND ANALYSIS Dsprites Dataset: We first evaluate the performance of DynamicVAE on learning disentangled representations using dSprites. ...
arXiv:2009.06795v2
fatcat:lquqqp6iwrguridmfhg5bfyqjm