# Fast Gradient-Based Inference with Continuous Latent Variable Models in Auxiliary Form

arXiv: https://arxiv.org/abs/1306.0733 · HTML: https://mlsanity.com/paper/1306.0733/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2013.

## Built on by (most cited first, 5 of 5)

- [DeepCAVE: An Interactive Analysis Tool for Automated Machine Learning](https://mlsanity.com/paper/2206.03493/) (2022)
- [Convex Smoothed Autoencoder-Optimal Transport model](https://mlsanity.com/paper/2101.05679/) (2021)
- [Deep Learning and Synthetic Media](https://mlsanity.com/paper/2205.05764/) (2022)
- [Variational Transfer Learning using Cross-Domain Latent Modulation](https://mlsanity.com/paper/2205.15523/) (2022)
- [Realistic Hair Synthesis with Generative Adversarial Networks](https://mlsanity.com/paper/2209.12875/) (2022)

## Abstract (arXiv)

We propose a technique for increasing the efficiency of gradient-based inference and learning in Bayesian networks with multiple layers of continuous latent vari- ables. We show that, in many cases, it is possible to express such models in an auxiliary form, where continuous latent variables are conditionally deterministic given their parents and a set of independent auxiliary variables. Variables of mod- els in this auxiliary form have much larger Markov blankets, leading to significant speedups in gradient-based inference, e.g. rapid mixing Hybrid Monte Carlo and efficient gradient-based optimization. The relative efficiency is confirmed in ex- periments.