Stochastic Diffusion: A Diffusion Probabilistic Model for Stochastic Time Series Forecasting
This work addresses forecasting for stochastic time series, potentially benefiting the medical community, but appears incremental as it adapts diffusion models to a specific domain.
The paper tackles the challenge of modeling highly stochastic time series data by proposing a Stochastic Diffusion (StochDiff) model that learns data-driven prior knowledge to capture complex temporal dynamics and inherent uncertainty, demonstrating effectiveness in real-world datasets and an application for surgical guidance.
Recent innovations in diffusion probabilistic models have paved the way for significant progress in image, text and audio generation, leading to their applications in generative time series forecasting. However, leveraging such abilities to model highly stochastic time series data remains a challenge. In this paper, we propose a novel Stochastic Diffusion (StochDiff) model which learns data-driven prior knowledge at each time step by utilizing the representational power of the stochastic latent spaces to model the variability of the multivariate time series data. The learnt prior knowledge helps the model to capture complex temporal dynamics and the inherent uncertainty of the data. This improves its ability to model highly stochastic time series data. Through extensive experiments on real-world datasets, we demonstrate the effectiveness of our proposed model on stochastic time series forecasting. Additionally, we showcase an application of our model for real-world surgical guidance, highlighting its potential to benefit the medical community.