Abstract: In the work to be presented, we leverage the power of latent diffusion models to generate synthetic time series tabular data. Along with the temporal and feature correlations, the heterogeneous nature of the feature in the table has been one of the main obstacles in time series tabular data modeling. We tackle this problem by combining the ideas of the variational auto-encoder (VAE) and the denoising diffusion probabilistic model (DDPM). Our model, named “TimeAutoDiff,” has several key advantages, including (1) Generality, the ability to handle the broad spectrum of time series tabular data from single to multi-sequence datasets; (2) Good fidelity and utility guarantees: numerical experiments on six publicly available datasets demonstrating significant improvements over state-of-the-art models in generating time series tabular data, across four metrics measuring fidelity and utility; (3) Fast sampling speed: entire time series data generation as opposed to the sequential data sampling schemes implemented in the existing diffusion-based models, eventually leading to significant improvements in sampling speed, (4) Entity conditional generation: the first implementation of conditional generation of multi-sequence time series tabular data with heterogenous features in the literature, enabling scenario exploration across multiple scientific and engineering domains.

About the speaker: Dr. Namjoon Suh is a UCLA adjunct assistant professor. He is an IDRE fellow and is associated with Prof. Dr. Guang Cheng’s lab in the UCLA Statistics and Data Science Department. He obtained his Machine Learning Ph.D. degree at Stewart School of Industrial & Systems Engineering, Georgia Tech, in December 2022 and earned an M.Sc. in Statistics at Georgia Tech in 2018. Before Georgia Tech, he received a B.Sc. degree from Korea University in 2015, majoring in Industrial Engineering.