SigDiffusions: Score-Based Diffusion Models for Long Time Series via Log-Signature Embeddings
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 proc...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | 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. |
---|---|
DOI: | 10.48550/arxiv.2406.10354 |