TSGM: Regular and Irregular Time-series Generation using Score-based Generative Models
By: Haksoo Lim , Jaehoon Lee , Sewon Park and more
Potential Business Impact:
Creates realistic fake time data for any use.
Score-based generative models (SGMs) have demonstrated unparalleled sampling quality and diversity in numerous fields, such as image generation, voice synthesis, and tabular data synthesis, etc. Inspired by those outstanding results, we apply SGMs to synthesize time-series by learning its conditional score function. To this end, we present a conditional score network for time-series synthesis, deriving a denoising score matching loss tailored for our purposes. In particular, our presented denoising score matching loss is the conditional denoising score matching loss for time-series synthesis. In addition, our framework is such flexible that both regular and irregular time-series can be synthesized with minimal changes to our model design. Finally, we obtain exceptional synthesis performance on various time-series datasets, achieving state-of-the-art sampling diversity and quality.
Similar Papers
Causal Time Series Generation via Diffusion Models
Machine Learning (CS)
Makes computer predictions account for real-world causes.
A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equations
Machine Learning (CS)
Helps computers create new molecules for medicine.
Algorithm- and Data-Dependent Generalization Bounds for Score-Based Generative Models
Machine Learning (Stat)
Helps AI learn to make better, more realistic pictures.