# The continuous categorical: a novel simplex-valued exponential family

arXiv: https://arxiv.org/abs/2002.08563 · HTML: https://mlsanity.com/paper/2002.08563/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2020.

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

- [Efficient-VDVAE: Less is more](https://mlsanity.com/paper/2203.13751/) (2022)
- [ConvBKI: Real-Time Probabilistic Semantic Mapping Network with Quantifiable Uncertainty](https://mlsanity.com/paper/2310.16020/) (2023)
- [Evidential Semantic Mapping in Off-road Environments with Uncertainty-aware Bayesian Kernel Inference](https://mlsanity.com/paper/2403.14138/) (2024)
- [Towards noise contrastive estimation with soft targets for conditional models](https://mlsanity.com/paper/2404.14076/) (2024)
- [Learning Cut Generating Functions for Integer Programming](https://mlsanity.com/paper/2405.13992/) (2024)
- [Data Augmentation for Compositional Data: Advancing Predictive Models of the Microbiome](https://mlsanity.com/paper/2205.09906/) (2022)
- [CosmoBench: A Multiscale, Multiview, Multitask Cosmology Benchmark for Geometric Deep Learning](https://mlsanity.com/paper/2507.03707/) (2025)
- [Sparse Communication via Mixed Distributions](https://mlsanity.com/paper/2108.02658/) (2021)
- [DBCal: Density Based Calibration of classifier predictions for uncertainty quantification](https://mlsanity.com/paper/2204.00150/) (2022)
- [On the Normalizing Constant of the Continuous Categorical Distribution](https://mlsanity.com/paper/2204.13290/) (2022)
- [Diarisation using location tracking with agglomerative clustering](https://mlsanity.com/paper/2109.10598/) (2021)
- [Joint speaker diarisation and tracking in switching state-space model](https://mlsanity.com/paper/2109.11140/) (2021)

## Abstract (arXiv)

Simplex-valued data appear throughout statistics and machine learning, for example in the context of transfer learning and compression of deep networks. Existing models for this class of data rely on the Dirichlet distribution or other related loss functions; here we show these standard choices suffer systematically from a number of limitations, including bias and numerical issues that frustrate the use of flexible network models upstream of these distributions. We resolve these limitations by introducing a novel exponential family of distributions for modeling simplex-valued data - the continuous categorical, which arises as a nontrivial multivariate generalization of the recently discovered continuous Bernoulli. Unlike the Dirichlet and other typical choices, the continuous categorical results in a well-behaved probabilistic loss function that produces unbiased estimators, while preserving the mathematical simplicity of the Dirichlet. As well as exploring its theoretical properties, we introduce sampling methods for this distribution that are amenable to the reparameterization trick, and evaluate their performance. Lastly, we demonstrate that the continuous categorical outperforms standard choices empirically, across a simulation study, an applied example on multi-party elections, and a neural network compression task.