TimeBridge: Better Diffusion Prior Design with Bridge Models for Time Series Generation

TL;DR

TimeBridge introduces a novel diffusion bridge framework for time series generation, addressing limitations of standard Gaussian priors by learning paths between priors and data distributions, leading to improved synthesis quality.

Contribution

The paper proposes TimeBridge, a flexible diffusion-based framework with tailored priors for better time series synthesis, surpassing standard models.

Findings

Data-driven priors outperform standard diffusion models

TimeBridge effectively models temporal properties of time series

Framework supports both unconditional and conditional generation

Abstract

Time series generation is widely used in real-world applications such as simulation, data augmentation, and hypothesis testing. Recently, diffusion models have emerged as the de facto approach to time series generation, enabling diverse synthesis scenarios. However, the fixed standard-Gaussian diffusion prior may be ill-suited for time series data, which exhibit properties such as temporal order and fixed time points. In this paper, we propose TimeBridge, a framework that flexibly synthesizes time series data by using diffusion bridges to learn paths between a chosen prior and the data distribution. We then explore several prior designs tailored to time series synthesis. Our framework covers (i) data- and time-dependent priors for unconditional generation and (ii) scale-preserving priors for conditional generation. Experiments show that our framework with data-driven priors outperforms standard diffusion models on time series generation.