From Noise to Laws: Regularized Time-Series Forecasting via Denoised Dynamic Graphs
This work solves forecasting challenges for domains requiring robust predictions, though it appears incremental as it combines existing techniques like diffusion and graph encoders.
The paper tackled long-horizon multivariate time-series forecasting by addressing denoising, tracking dependencies, and ensuring stability, resulting in consistent state-of-the-art performance with strong MSE and MAE gains on six benchmarks.
Long-horizon multivariate time-series forecasting is challenging because realistic predictions must (i) denoise heterogeneous signals, (ii) track time-varying cross-series dependencies, and (iii) remain stable and physically plausible over long rollout horizons. We present PRISM, which couples a score-based diffusion preconditioner with a dynamic, correlation-thresholded graph encoder and a forecast head regularized by generic physics penalties. We prove contraction of the induced horizon dynamics under mild conditions and derive Lipschitz bounds for graph blocks, explaining the model's robustness. On six standard benchmarks , PRISM achieves consistent SOTA with strong MSE and MAE gains.