DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment

arXiv:2510.24574v2 Announce Type: replace-cross Abstract: Training time-series forecasting models requires aligning the conditional distribution of model forecasts with that of the label sequence. The standard direct forecast (DF) approach resorts to minimizing the conditional negative log-likelihood, typically estimated by the mean squared error. However, this estimation proves biased when the label sequence exhibits autocorrelation. In this paper, we propose DistDF, which achieves alignment by