Get Started
Research questionHow can diffusion models forecast multivariate time series reliably when variables differ in noise and observations are corrupted?Multivariate series can contain variables with different evolutionary patterns and noise levels, making shared conditioning signals prone to trusting unreliable observations. Corruption can further distort the resulting probabilistic forecasts.
Diffusion Models
Machine Learning
Statistical Machine Learning
Latest papersRecent research connected to this question, newest first.DynG-Diff: A State-Aware Dynamic Guidance Diffusion Framework for Probabilistic Time Series ForecastingThe source presents DynG-Diff, which uses an unconditional diffusion backbone and a state-aware policy network to infer variable reliability from noisy states and denoising estimates during inference. Its reported evidence comes from real-world benchmarks, where it shows competitive probabilistic forecasting and improved robustness under severe observation corruption; the abstract does not specify the datasets, corruption protocols, or metrics.research paper · Sep 2, 2026
Related questions
How can historical base-model residuals robustly correct multivariate forecasts without overcorrection?How can multivariate time-series imputers recover structured gaps under high missingness?How can corporate distress be forecast from high-dimensional, mixed-frequency data with right-censored outcomes?How can reinforcement learning post-training for diffusion models avoid objective mismatch and high-variance updates?
Home
Topics
Search
Library