DeepAI AI Chat
Log In Sign Up

RegFlow: Probabilistic Flow-based Regression for Future Prediction

by   Maciej Zieba, et al.

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.


page 2

page 8


Modeling the evolution of temporal knowledge graphs with uncertainty

Forecasting future events is a fundamental challenge for temporal knowle...

Diverse Video Generation using a Gaussian Process Trigger

Generating future frames given a few context (or past) frames is a chall...

Conditional Flow Variational Autoencoders for Structured Sequence Prediction

Prediction of future states of the environment and interacting agents is...

TreeFlow: Going beyond Tree-based Gaussian Probabilistic Regression

The tree-based ensembles are known for their outstanding performance for...

Predicting the Future Behavior of a Time-Varying Probability Distribution

We study the problem of predicting the future, though only in the probab...

PLAN-B: Predicting Likely Alternative Next Best Sequences for Action Prediction

Action prediction focuses on anticipating actions before they happen. Re...