# Interpreting Rate-Distortion of Variational Autoencoder and Using Model Uncertainty for Anomaly Detection

arXiv: https://arxiv.org/abs/2005.01889 · HTML: https://mlsanity.com/paper/2005.01889/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2020.

## Built on by (most cited first, 10 of 10)

- [Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve](https://mlsanity.com/paper/2212.03905/) (2022)
- [Confidence-Aware Graph Neural Networks for Learning Reliability Assessment Commitments](https://mlsanity.com/paper/2211.15755/) (2022)
- [Learning Dynamics in Linear VAE: Posterior Collapse Threshold, Superfluous Latent Space Pitfalls, and Speedup with KL Annealing](https://mlsanity.com/paper/2310.15440/) (2023)
- [Deep Data Density Estimation through Donsker-Varadhan Representation](https://mlsanity.com/paper/2104.06612/) (2021)
- [High-dimensional Asymptotics of VAEs: Threshold of Posterior Collapse and Dataset-Size Dependence of Rate-Distortion Curve](https://mlsanity.com/paper/2309.07663/) (2023)
- [Conditioning Latent-Space Clusters for Real-World Anomaly Classification](https://mlsanity.com/paper/2309.09676/) (2023)
- [MSS-PAE: Saving Autoencoder-based Outlier Detection from Unexpected Reconstruction](https://mlsanity.com/paper/2304.00709/) (2023)
- [Unsupervised Anomaly Detection Using Diffusion Trend Analysis for Display Inspection](https://mlsanity.com/paper/2407.09578/) (2024)
- [RDD: Pareto Analysis of the Rate-Distortion-Distinguishability Trade-off](https://mlsanity.com/paper/2509.24805/) (2025)
- [Taming Audio VAEs via Target-KL Regularization](https://mlsanity.com/paper/2605.17085/) (2026)

## Abstract (arXiv)

Building a scalable machine learning system for unsupervised anomaly detection via representation learning is highly desirable. One of the prevalent methods is using a reconstruction error from variational autoencoder (VAE) via maximizing the evidence lower bound. We revisit VAE from the perspective of information theory to provide some theoretical foundations on using the reconstruction error, and finally arrive at a simpler and more effective model for anomaly detection. In addition, to enhance the effectiveness of detecting anomalies, we incorporate a practical model uncertainty measure into the metric. We show empirically the competitive performance of our approach on benchmark datasets.