# Deep Exponential Families

arXiv: https://arxiv.org/abs/1411.2581 · HTML: https://mlsanity.com/paper/1411.2581/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2014.

## Built on by (most cited first, 12 of 12)

- [Normalizing Flows for Interventional Density Estimation](https://mlsanity.com/paper/2209.06203/) (2022)
- [Natural Posterior Network: Deep Bayesian Uncertainty for Exponential Family Distributions](https://mlsanity.com/paper/2105.04471/) (2021)
- [Survival Mixture Density Networks](https://mlsanity.com/paper/2208.10759/) (2022)
- [A Unifying Perspective on Non-Stationary Kernels for Deeper Gaussian Processes](https://mlsanity.com/paper/2309.10068/) (2023)
- [Deep Generative Models, Synthetic Tabular Data, and Differential Privacy: An Overview and Synthesis](https://mlsanity.com/paper/2307.15424/) (2023)
- [Contrastive Learning of Temporal Distinctiveness for Survival Analysis in Electronic Health Records](https://mlsanity.com/paper/2308.13104/) (2023)
- [Deep Discrete Encoders: Identifiable Deep Generative Models for Rich Data with Discrete Latent Layers](https://mlsanity.com/paper/2501.01414/) (2025)
- [Scalable Weibull Graph Attention Autoencoder for Modeling Document Networks](https://mlsanity.com/paper/2410.09696/) (2024)
- [Convolutional Deep Exponential Families](https://mlsanity.com/paper/2110.14800/) (2021)
- [Multinomial belief networks for healthcare data](https://mlsanity.com/paper/2311.16909/) (2023)
- [Composite Survival Analysis: Learning with Auxiliary Aggregated Baselines and Survival Scores](https://mlsanity.com/paper/2312.05854/) (2023)
- [Multiple Invertible and Partial-Equivariant Function for Latent Vector Transformation to Enhance Disentanglement in VAEs](https://mlsanity.com/paper/2502.03740/) (2025)

## Abstract (arXiv)

We describe textitdeep exponential families (DEFs), a class of latent variable models that are inspired by the hidden structures used in deep neural networks. DEFs capture a hierarchy of dependencies between latent variables, and are easily generalized to many settings through exponential families. We perform inference using recent "black box" variational inference techniques. We then evaluate various DEFs on text and combine multiple DEFs into a model for pairwise recommendation data. In an extensive study, we show that going beyond one layer improves predictions for DEFs. We demonstrate that DEFs find interesting exploratory structure in large data sets, and give better predictive performance than state-of-the-art models.