Space-Time Diffusion Bridge

TL;DR

This paper introduces a space-time diffusion bridge method for generating high-dimensional synthetic data samples that are independent and identically distributed, leveraging stochastic processes and optimal transport techniques.

Contribution

It presents a novel space-time diffusion approach combining linear, diffusion bridge, and nonlinear processes for efficient high-dimensional data synthesis.

Findings

Validated through numerical experiments

Potential for simulation-free inference

Lays groundwork for future theoretical development

Abstract

In this study, we introduce a novel method for generating new synthetic samples that are independent and identically distributed (i.i.d.) from high-dimensional real-valued probability distributions, as defined implicitly by a set of Ground Truth (GT) samples. Central to our method is the integration of space-time mixing strategies that extend across temporal and spatial dimensions. Our methodology is underpinned by three interrelated stochastic processes designed to enable optimal transport from an easily tractable initial probability distribution to the target distribution represented by the GT samples: (a) linear processes incorporating space-time mixing that yield Gaussian conditional probability densities, (b) their diffusion bridge analogs that are conditioned to the initial and final state vectors, and (c) nonlinear stochastic processes refined through score-matching techniques. The crux of our training regime involves fine-tuning the nonlinear model, and potentially the linear models -- to align closely with the GT data. We validate the efficacy of our space-time diffusion approach with numerical experiments, laying the groundwork for more extensive future theory and experiments to fully authenticate the method, particularly providing a more efficient (possibly simulation-free) inference.