# Spurious samples in deep generative models: bug or feature?

arXiv: https://arxiv.org/abs/1810.01876 · HTML: https://mlsanity.com/paper/1810.01876/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2018.

## Built on by (most cited first, 2 of 2)

- [Active Divergence with Generative Deep Learning -- A Survey and Taxonomy](https://mlsanity.com/paper/2107.05599/) (2021)
- [Challenges in creative generative models for music: a divergence maximization perspective](https://mlsanity.com/paper/2211.08856/) (2022)

## Abstract (arXiv)

Traditional wisdom in generative modeling literature is that spurious samples that a model can generate are errors and they should be avoided. Recent research, however, has shown interest in studying or even exploiting such samples instead of eliminating them. In this paper, we ask the question whether such samples can be eliminated all together without sacrificing coverage of the generating distribution. For the class of models we consider, we experimentally demonstrate that this is not possible without losing the ability to model some of the test samples. While our results need to be confirmed on a broader set of model families, these initial findings provide partial evidence that spurious samples share structural properties with the learned dataset, which, in turn, suggests they are not simply errors but a feature of deep generative nets.