Sig-Wasserstein GANs for Time Series Generation

TL;DR

This paper introduces SigWGAN, a novel time-series generator that combines stochastic differential equations with a signature-based Wasserstein metric, enabling high-fidelity synthetic data generation for financial and synthetic datasets.

Contribution

The paper presents a new time-series GAN model that leverages signature $W_1$ metric and stochastic differential equations, simplifying training and improving sample quality.

Findings

Successfully generates high-fidelity synthetic financial data.

Validates model on synthetic and real datasets.

Transforms GAN training into supervised learning.

Abstract

Synthetic data is an emerging technology that can significantly accelerate the development and deployment of AI machine learning pipelines. In this work, we develop high-fidelity time-series generators, the SigWGAN, by combining continuous-time stochastic models with the newly proposed signature $W_1$ metric. The former are the Logsig-RNN models based on the stochastic differential equations, whereas the latter originates from the universal and principled mathematical features to characterize the measure induced by time series. SigWGAN allows turning computationally challenging GAN min-max problem into supervised learning while generating high fidelity samples. We validate the proposed model on both synthetic data generated by popular quantitative risk models and empirical financial data. Codes are available at https://github.com/SigCGANs/Sig-Wasserstein-GANs.git.