# Deep Modeling of Non-Gaussian Aleatoric Uncertainty

arXiv: https://arxiv.org/abs/2405.20513 · HTML: https://mlsanity.com/paper/2405.20513/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 41 references that are in the map.
- First posted on arXiv 30 May 2024.

## Builds on (most cited first, 16 of 16)

- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Normalizing Flows for Probabilistic Modeling and Inference](https://mlsanity.com/paper/1912.02762/) (2019)
- [Masked Autoregressive Flow for Density Estimation](https://mlsanity.com/paper/1705.07057/) (2017)
- [Improving Variational Inference with Inverse Autoregressive Flow](https://mlsanity.com/paper/1606.04934/) (2016)
- [On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks](https://mlsanity.com/paper/2203.09168/) (2022)
- [Conditional Density Estimation with Neural Networks: Best Practices and Benchmarks](https://mlsanity.com/paper/1903.00954/) (2019)
- [Multivariate Uncertainty in Deep Learning](https://mlsanity.com/paper/1910.14215/) (2019)
- [Neural Density Estimation and Likelihood-free Inference](https://mlsanity.com/paper/1910.13233/) (2019)
- [A Comparison of Uncertainty Estimation Approaches in Deep Learning Components for Autonomous Vehicle Applications](https://mlsanity.com/paper/2006.15172/) (2020)
- [Deep Distribution Regression](https://mlsanity.com/paper/1903.06023/) (2019)
- [Competency Assessment for Autonomous Agents using Deep Generative Models](https://mlsanity.com/paper/2203.12670/) (2022)
- [Learning to Forecast Aleatoric and Epistemic Uncertainties over Long Horizon Trajectories](https://mlsanity.com/paper/2302.08669/) (2023)
- [Deconvolutional Density Network: Modeling Free-Form Conditional Distributions](https://mlsanity.com/paper/2105.14367/) (2021)
- [Better Conditional Density Estimation for Neural Networks](https://mlsanity.com/paper/1606.02321/) (2016)
- [Vision-Based Terrain Relative Navigation on High-Altitude Balloon and Sub-Orbital Rocket](https://mlsanity.com/paper/2302.08011/) (2023)

## Built on by (most cited first, 1 of 1)

- [HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Model](https://mlsanity.com/paper/2510.05054/) (2025)

## Abstract (arXiv)

Deep learning offers promising new ways to accurately model aleatoric uncertainty in robotic state estimation systems, particularly when the uncertainty distributions do not conform to traditional assumptions of being fixed and Gaussian. In this study, we formulate and evaluate three fundamental deep learning approaches for conditional probability density modeling to quantify non-Gaussian aleatoric uncertainty: parametric, discretized, and generative modeling. We systematically compare the respective strengths and weaknesses of these three methods on simulated non-Gaussian densities as well as on real-world terrain-relative navigation data. Our results show that these deep learning methods can accurately capture complex uncertainty patterns, highlighting their potential for improving the reliability and robustness of estimation systems.