Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusion
Temporal data such as time series can be viewed as discretized measurements of the underlying function. To build a generative model for such data we have to model the stochastic process that governs it. We propose a solution by defining the denoising diffusion model in the function space which also allows us to naturally handle irregularly-sampled observations. The forward process gradually adds noise to functions, preserving their continuity, while the learned reverse process removes the noise and returns functions as new samples. To this end, we define suitable noise sources and introduce novel denoising and score-matching models. We show how our method can be used for multivariate probabilistic forecasting and imputation, and how our model can be interpreted as a neural process.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingImputationTime SeriesTime Series AnalysisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ProGen: Revisiting Probabilistic Spatial-Temporal Time Series Forecasting from a Continuous Generative Perspective Using Stochastic Differential Equations
Accurate forecasting of spatiotemporal data remains challenging due to complex spatial dependencies and temporal dynamics. The inherent uncertainty and variability in such data often render deterministic models insuffici…
DenoisingTime SeriesTime Series ForecastingHGAN-SDEs: Learning Neural Stochastic Differential Equations with Hermite-Guided Adversarial Training
Neural Stochastic Differential Equations (Neural SDEs) provide a principled framework for modeling continuous-time stochastic processes and have been widely adopted in fields ranging from physics to finance. Recent advan…
Scalable Gradients and Variational Inference for Stochastic Differential Equations
We derive reverse-mode (or adjoint) automatic differentiation for solutions of stochastic differential equations (SDEs), allowing time-efficient and constant-memory computation of pathwise gradients, a continuous-time an…
Time SeriesTime Series AnalysisVariational InferenceStochastic Deep Learning: A Probabilistic Framework for Modeling Uncertainty in Structured Temporal Data
I propose a novel framework that integrates stochastic differential equations (SDEs) with deep generative models to improve uncertainty quantification in machine learning applications involving structured and temporal da…
RainODE: Continuous-Time Precipitation Forecasting with Latent Neural ODEs
In precipitation forecasting, not only accuracy but also temporal resolution is critical. However, increasing temporal resolution is constrained by observational limitations and the computational cost of dense discrete m…
Precipitation Forecasting