SigDiffusions: Score-Based Diffusion Models for Long Time Series via Log-Signature Embeddings
Barancikova, Barbora, Huang, Zhuoyue, Salvi, Cristopher
–arXiv.org Artificial Intelligence
Score-based diffusion models have recently emerged as state-of-the-art generative models for a variety of data modalities. Nonetheless, it remains unclear how to adapt these models to generate long multivariate time series. Viewing a time series as the discretization of an underlying continuous process, we introduce SigDiffusion, a novel diffusion model operating on log-signature embeddings of the data. The forward and backward processes gradually perturb and denoise log-signatures preserving their algebraic structure. To recover a signal from its log-signature, we provide new closed-form inversion formulae expressing the coefficients obtained by expanding the signal in a given basis (e.g. Fourier or orthogonal polynomials) as explicit polynomial functions of the log-signature. Finally, we show that combining SigDiffusion with these inversion formulae results in highly realistic time series generation, competitive with the current state-of-the-art on various datasets of synthetic and real-world examples.
arXiv.org Artificial Intelligence
Jun-14-2024
- Country:
- North America > United States
- New York > New York County > New York City (0.14)
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.14)
- North America > United States
- Genre:
- Research Report (0.63)
- Industry:
- Energy (0.68)
- Information Technology > Security & Privacy (0.46)
- Technology: