# Automatic Relevance Determination For Deep Generative Models

arXiv: https://arxiv.org/abs/1505.07765 · HTML: https://mlsanity.com/paper/1505.07765/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2015.

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

- [Joint Model and Data Sparsification via the Marginal Likelihood](https://mlsanity.com/paper/2605.29908/) (2026)

## Abstract (arXiv)

A recurring problem when building probabilistic latent variable models is regularization and model selection, for instance, the choice of the dimensionality of the latent space. In the context of belief networks with latent variables, this problem has been adressed with Automatic Relevance Determination (ARD) employing Monte Carlo inference. We present a variational inference approach to ARD for Deep Generative Models using doubly stochastic variational inference to provide fast and scalable learning. We show empirical results on a standard dataset illustrating the effects of contracting the latent space automatically. We show that the resulting latent representations are significantly more compact without loss of expressive power of the learned models.