# RegFlow: Probabilistic Flow-based Regression for Future Prediction

arXiv: https://arxiv.org/abs/2011.14620 · HTML: https://mlsanity.com/paper/2011.14620/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2020.

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

- [Neural Groundplans: Persistent Neural Scene Representations from a Single Image](https://mlsanity.com/paper/2207.11232/) (2022)
- [HyperNeRFGAN: Hypernetwork approach to 3D NeRF GAN](https://mlsanity.com/paper/2301.11631/) (2023)
- [On out-of-distribution detection with Bayesian neural networks](https://mlsanity.com/paper/2110.06020/) (2021)
- [Modeling Uncertainty in Personalized Emotion Prediction with Normalizing Flows](https://mlsanity.com/paper/2312.06034/) (2023)
- [Predicting Physical World Destinations for Commands Given to Self-Driving Cars](https://mlsanity.com/paper/2112.05419/) (2021)
- [Uncertainty estimation under model misspecification in neural network regression](https://mlsanity.com/paper/2111.11763/) (2021)
- [TreeFlow: Going beyond Tree-based Gaussian Probabilistic Regression](https://mlsanity.com/paper/2206.04140/) (2022)

## Abstract (arXiv)

Predicting future states or actions of a given system remains a fundamental, yet unsolved challenge of intelligence, especially in the scope of complex and non-deterministic scenarios, such as modeling behavior of humans. Existing approaches provide results under strong assumptions concerning unimodality of future states, or, at best, assuming specific probability distributions that often poorly fit to real-life conditions. In this work we introduce a robust and flexible probabilistic framework that allows to model future predictions with virtually no constrains regarding the modality or underlying probability distribution. To achieve this goal, we leverage a hypernetwork architecture and train a continuous normalizing flow model. The resulting method dubbed RegFlow achieves state-of-the-art results on several benchmark datasets, outperforming competing approaches by a significant margin.