Conditionally Whitened Generative Models for Probabilistic Time Series Forecasting

arXiv:2509.20928v3 Announce Type: replace-cross Abstract: Probabilistic forecasting of multivariate time series is challenging due to non-stationarity, inter-variable dependencies, and distribution shifts. While recent diffusion and flow matching models have shown promise, the...

🔗 Read more: https://arxiv.org/abs/2509.20928

#News #Energy #Software #WorldNews #Business #Policy #Academic