# Information Constraints on Auto-Encoding Variational Bayes

Source: [Information Constraints on Auto-Encoding Variational Bayes](<https://www.sota2.com/research/paper/68fa5edf1e209131ce9e5ecc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T19:02:51.915Z

Authors: Romain Lopez, Jeffrey Regier, Michael I. Jordan, Nir Yosef

Published: 2018-05-22T15:45:14.000Z

## Abstract

Parameterizing the approximate posterior of a generative model with neural networks has become a common theme in recent machine learning research. While providing appealing flexibility, this approach makes it difficult to impose or assess structural constraints such as conditional independence. We propose a framework for learning representations that relies on Auto-Encoding Variational Bayes and whose search space is constrained via kernel-based measures of independence. In particular, our method employs the $d$-variable Hilbert-Schmidt Independence Criterion (dHSIC) to enforce independence between the latent representations and arbitrary nuisance factors. We show how to apply this method to a range of problems, including the problems of learning invariant representations and the learning of interpretable representations. We also present a full-fledged application to single-cell RNA sequencing (scRNA-seq). In this setting the biological signal is mixed in complex ways with sequencing errors and sampling effects. We show that our method out-performs the state-of-the-art in this domain.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Time point Subspace Disentanglement on Malaria scRNA-seq](<https://www.sota2.com/research/sota/time-point-subspace-disentanglement-on-malaria-scrna-seq.md>): Time point Subspace Disentanglement; Malaria scRNA-seq; Silhouette Score (Infection): -0.069.

- [Subspace Alignment on Malaria scRNA-seq](<https://www.sota2.com/research/sota/subspace-alignment-on-malaria-scrna-seq.md>): Subspace Alignment; Malaria scRNA-seq; Grassmann Distance: 3.598.

- [Infection Subspace Disentanglement on Malaria scRNA-seq](<https://www.sota2.com/research/sota/infection-subspace-disentanglement-on-malaria-scrna-seq.md>): Infection Subspace Disentanglement; Malaria scRNA-seq; Silhouette Score (Infection Label): -0.015.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1805.08672>)

[PDF](<https://arxiv.org/pdf/1805.08672.pdf>)