# MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders

arXiv: https://arxiv.org/abs/1901.01498 · HTML: https://mlsanity.com/paper/1901.01498/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jan 2019.

## Built on by (most cited first, 15 of 15)

- [Score-based Generative Modeling in Latent Space](https://mlsanity.com/paper/2106.05931/) (2021)
- [Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models](https://mlsanity.com/paper/2103.04922/) (2021)
- [Preventing Oversmoothing in VAE via Generalized Variance Parameterization](https://mlsanity.com/paper/2102.08663/) (2021)
- [Continual Variational Autoencoder Learning via Online Cooperative Memorization](https://mlsanity.com/paper/2207.10131/) (2022)
- [Truth-Conditional Captioning of Time Series Data](https://mlsanity.com/paper/2110.01839/) (2021)
- [A Tale of Two Latent Flows: Learning Latent Space Normalizing Flow with Short-run Langevin Flow for Approximate Inference](https://mlsanity.com/paper/2301.09300/) (2023)
- [Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness](https://mlsanity.com/paper/2110.12381/) (2021)
- [Cooperation in the Latent Space: The Benefits of Adding Mixture Components in Variational Autoencoders](https://mlsanity.com/paper/2209.15514/) (2022)
- [ReliCD: A Reliable Cognitive Diagnosis Framework with Confidence Awareness](https://mlsanity.com/paper/2401.10749/) (2023)
- [A Non-negative VAE:the Generalized Gamma Belief Network](https://mlsanity.com/paper/2408.03388/) (2024)
- [Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory](https://mlsanity.com/paper/2103.03905/) (2021)
- [Efficient Mixture Learning in Black-Box Variational Inference](https://mlsanity.com/paper/2406.07083/) (2024)
- [ELBD: Efficient score algorithm for feature selection on latent variables of VAE](https://mlsanity.com/paper/2111.08493/) (2021)
- [Explainable Recommender with Geometric Information Bottleneck](https://mlsanity.com/paper/2305.05331/) (2023)
- [Entropic Auto-Encoding via Implicit Free-Energy Minimization](https://mlsanity.com/paper/2605.16164/) (2026)

## Abstract (arXiv)

Variational Autoencoder (VAE), a simple and effective deep generative model, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations. However, recent studies demonstrate that, when equipped with expressive generative distributions (aka. decoders), VAE suffers from learning uninformative latent representations with the observation called KL Varnishing, in which case VAE collapses into an unconditional generative model. In this work, we introduce mutual posterior-divergence regularization, a novel regularization that is able to control the geometry of the latent space to accomplish meaningful representation learning, while achieving comparable or superior capability of density estimation. Experiments on three image benchmark datasets demonstrate that, when equipped with powerful decoders, our model performs well both on density estimation and representation learning.