# Variational Hyper-Encoding Networks

arXiv: https://arxiv.org/abs/2005.08482 · HTML: https://mlsanity.com/paper/2005.08482/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 May 2020.

## Built on by (most cited first, 5 of 5)

- [VTAE: Variational Transformer Autoencoder with Manifolds Learning](https://mlsanity.com/paper/2304.00948/) (2023)
- [Variational Mixture of HyperGenerators for Learning Distributions Over Functions](https://mlsanity.com/paper/2302.06223/) (2023)
- [Temporal Variational Implicit Neural Representations](https://mlsanity.com/paper/2506.01544/) (2025)
- [ID-Card Synthetic Generation: Toward a Simulated Bona fide Dataset](https://mlsanity.com/paper/2508.13078/) (2025)
- [Instance-Adaptive Parametrization for Amortized Variational Inference](https://mlsanity.com/paper/2604.06796/) (2026)

## Abstract (arXiv)

We propose a framework called HyperVAE for encoding distributions of distributions. When a target distribution is modeled by a VAE, its neural network parameters θ is drawn from a distribution p(θ) which is modeled by a hyper-level VAE. We propose a variational inference using Gaussian mixture models to implicitly encode the parameters θ into a low dimensional Gaussian distribution. Given a target distribution, we predict the posterior distribution of the latent code, then use a matrix-network decoder to generate a posterior distribution q(θ). HyperVAE can encode the parameters θ in full in contrast to common hyper-networks practices, which generate only the scale and bias vectors as target-network parameters. Thus HyperVAE preserves much more information about the model for each task in the latent space. We discuss HyperVAE using the minimum description length (MDL) principle and show that it helps HyperVAE to generalize. We evaluate HyperVAE in density estimation tasks, outlier detection and discovery of novel design classes, demonstrating its efficacy.