https://github.com/minitechy/betavae_recon
Augmenting Reconstruction Accuracy in beta-VAE Model through Linear Gaussian Framework
https://github.com/minitechy/betavae_recon
beta-vae machine-learning nonlinear-optimization numerical-analysis
Last synced: about 2 months ago
JSON representation
Augmenting Reconstruction Accuracy in beta-VAE Model through Linear Gaussian Framework
- Host: GitHub
- URL: https://github.com/minitechy/betavae_recon
- Owner: Minitechy
- Created: 2023-08-07T04:41:33.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2023-08-12T21:58:17.000Z (almost 2 years ago)
- Last Synced: 2025-03-28T17:24:45.090Z (about 2 months ago)
- Topics: beta-vae, machine-learning, nonlinear-optimization, numerical-analysis
- Language: Jupyter Notebook
- Homepage:
- Size: 1.19 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Abstract:
Variational Autoencoders (VAEs) have garnered substantial attention as generative models for producing lower-dimensional representations of high-dimensional data. The $\beta$-VAE model employs the hyperparameter $\beta$ to strike a balance between reconstruction accuracy and disentanglement. This study exclusively targets the enhancement of reconstruction accuracy in the linear Gaussian $\beta$-VAE model by introducing three variants: $\gamma$-VAE with both arbitrary and diagonalized $\Sigma_{Z}$, as well as $\gamma\lambda$-VAE with diagonalized $\Sigma_{Z}$. We commence by deriving closed-form solutions for all three proposed frameworks using gradient-based and iterative methods. This demonstration of consistency between approaches highlights the robustness of our findings. Subsequently, we perform comprehensive numerical experiments employing the Blahut-Arimoto algorithm. These experiments underscore the benefits of utilizing a diagonalized positive definite $\Sigma_{Z}$ over an arbitrary one, leading to more informative numerical outcomes and augmented control over reconstruction accuracy. Furthermore, the introduction of an additional hyperparameter $\lambda$ offers an avenue for further refining reconstruction accuracy control. In conclusion, the introduction of these three variants to the $\beta$-VAE model, combined with analytical and numerical analyses, underscores the potential for improved reconstruction accuracy through the strategic incorporation of additional hyperparameters and nuanced adjustments to the foundational framework.