
The authors propose a novel generative adversarial network (PCF-GAN) that incorporates the path characteristic function (PCF) as the principled representation of time series distribution into the discriminator to enhance its generative performance. The PCF-GAN also integrates an auto-encoder structure to enable simultaneous generation and reconstruction of complex time series data.


coremsg

generating-sequential-data-via-the-path-characteristic-function-of-measures-on-the-path-space


Generating Sequential Data via the Path Characteristic Function of Measures on the Path Space


title_rewrite


Diffusion-TS proposes an interpretable diffusion framework for generating high-quality time series data, showcasing state-of-the-art results in various analyses.


diffusion-ts-interpretable-diffusion-for-general-time-series-generation-at-iclr-2024


Diffusion-TS: Interpretable Diffusion for General Time Series Generation at ICLR 2024
