# Out-of-Distribution Detection using BiGAN and MDL

arXiv: https://arxiv.org/abs/2206.01851 · HTML: https://mlsanity.com/paper/2206.01851/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 31 references that are in the map.
- First posted on arXiv 3 Jun 2022.

## Builds on (most cited first, 11 of 11)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [Adversarial Feature Learning](https://mlsanity.com/paper/1605.09782/) (2016)
- [Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift](https://mlsanity.com/paper/1810.11953/) (2018)
- [Adversarially Learned Inference](https://mlsanity.com/paper/1606.00704/) (2016)
- [Input complexity and out-of-distribution detection with likelihood-based generative models](https://mlsanity.com/paper/1909.11480/) (2019)
- [Density of States Estimation for Out-of-Distribution Detection](https://mlsanity.com/paper/2006.09273/) (2020)
- [Model-agnostic out-of-distribution detection using combined statistical tests](https://mlsanity.com/paper/2203.01097/) (2022)
- [Group Anomaly Detection using Deep Generative Models](https://mlsanity.com/paper/1804.04876/) (2018)
- [Graph Coding for Model Selection and Anomaly Detection in Gaussian Graphical Models](https://mlsanity.com/paper/2102.02431/) (2021)

## Built on by (most cited first, 1 of 1)

- [Deep Generative Models for Physiological Signals: A Systematic Literature Review](https://mlsanity.com/paper/2307.06162/) (2023)

## Abstract (arXiv)

We consider the following problem: we have a large dataset of normal data available. We are now given a new, possibly quite small, set of data, and we are to decide if these are normal data, or if they are indicating a new phenomenon. This is a novelty detection or out-of-distribution detection problem. An example is in medicine, where the normal data is for people with no known disease, and the new dataset people with symptoms. Other examples could be in security. We solve this problem by training a bidirectional generative adversarial network (BiGAN) on the normal data and using a Gaussian graphical model to model the output. We then use universal source coding, or minimum description length (MDL) on the output to decide if it is a new distribution, in an implementation of Kolmogorov and Martin-L"of randomness. We apply the methodology to both MNIST data and a real-world electrocardiogram (ECG) dataset of healthy and patients with Kawasaki disease, and show better performance in terms of the ROC curve than similar methods.