# Kernel Conditional Exponential Family

arXiv: https://arxiv.org/abs/1711.05363 · HTML: https://mlsanity.com/paper/1711.05363/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2017.

## Built on by (most cited first, 7 of 7)

- [Dual Training of Energy-Based Models with Overparametrized Shallow Neural Networks](https://mlsanity.com/paper/2107.05134/) (2021)
- [Exponential Family Model-Based Reinforcement Learning via Score Matching](https://mlsanity.com/paper/2112.14195/) (2021)
- [On the failure of variational score matching for VAE models](https://mlsanity.com/paper/2210.13390/) (2022)
- [Scalable Personalised Item Ranking through Parametric Density Estimation](https://mlsanity.com/paper/2105.04769/) (2021)
- [Kernel Deformed Exponential Families for Sparse Continuous Attention](https://mlsanity.com/paper/2111.01222/) (2021)
- [Guiding Time-Varying Generative Models with Natural Gradients on Exponential Family Manifold](https://mlsanity.com/paper/2502.07650/) (2025)
- [Variance-Reduced Diffusion Sampling via Target Score Identity](https://mlsanity.com/paper/2601.01594/) (2026)

## Abstract (arXiv)

A nonparametric family of conditional distributions is introduced, which generalizes conditional exponential families using functional parameters in a suitable RKHS. An algorithm is provided for learning the generalized natural parameter, and consistency of the estimator is established in the well specified case. In experiments, the new method generally outperforms a competing approach with consistency guarantees, and is competitive with a deep conditional density model on datasets that exhibit abrupt transitions and heteroscedasticity.