# Conditional Inference in Pre-trained Variational Autoencoders via Cross-coding

arXiv: https://arxiv.org/abs/1805.07785 · HTML: https://mlsanity.com/paper/1805.07785/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2018.

## Built on by (most cited first, 4 of 4)

- [Conditional Image Generation by Conditioning Variational Auto-Encoders](https://mlsanity.com/paper/2102.12037/) (2021)
- [Simultaneous Missing Value Imputation and Structure Learning with Groups](https://mlsanity.com/paper/2110.08223/) (2021)
- [Classification and Uncertainty Quantification of Corrupted Data using Semi-Supervised Autoencoders](https://mlsanity.com/paper/2105.13393/) (2021)
- [Posterior Consistency for Missing Data in Variational Autoencoders](https://mlsanity.com/paper/2310.16648/) (2023)

## Abstract (arXiv)

Variational Autoencoders (VAEs) are a popular generative model, but one in which conditional inference can be challenging. If the decomposition into query and evidence variables is fixed, conditional VAEs provide an attractive solution. To support arbitrary queries, one is generally reduced to Markov Chain Monte Carlo sampling methods that can suffer from long mixing times. In this paper, we propose an idea we term cross-coding to approximate the distribution over the latent variables after conditioning on an evidence assignment to some subset of the variables. This allows generating query samples without retraining the full VAE. We experimentally evaluate three variations of cross-coding showing that (i) they can be quickly optimized for different decompositions of evidence and query and (ii) they quantitatively and qualitatively outperform Hamiltonian Monte Carlo.