Causal Future Prediction in a Minkowski Space-Time

TL;DR

This paper introduces a theoretical framework for causal future prediction using Minkowski space-time embeddings, leveraging light cones from relativity to improve causal inference in machine learning tasks.

Contribution

It proposes a novel, architecture- and task-independent method that embeds spatiotemporal data in Minkowski space-time with theoretical guarantees of causality.

Findings

Successful causal image synthesis demonstrated

Effective future video frame prediction achieved

Framework provides strong causal guarantees

Abstract

Estimating future events is a difficult task. Unlike humans, machine learning approaches are not regularized by a natural understanding of physics. In the wild, a plausible succession of events is governed by the rules of causality, which cannot easily be derived from a finite training set. In this paper we propose a novel theoretical framework to perform causal future prediction by embedding spatiotemporal information on a Minkowski space-time. We utilize the concept of a light cone from special relativity to restrict and traverse the latent space of an arbitrary model. We demonstrate successful applications in causal image synthesis and future video frame prediction on a dataset of images. Our framework is architecture- and task-independent and comes with strong theoretical guarantees of causal capabilities.