AI RESEARCH
TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecasting
arXiv CS.LG
•
ArXi:2511.18539v2 Announce Type: replace We propose TimePre, a simple framework that unifies the efficiency of Multilayer Perceptron (MLP)-based models with the distributional flexibility of Multiple Choice Learning (MCL) for Probabilistic Time-Series Forecasting (PTSF). Stabilized Instance Normalization (SIN), the core of TimePre, is a normalization layer that explicitly addresses the trade-off among accuracy, efficiency, and stability. SIN stabilizes the hybrid architecture by correcting channel-wise statistical shifts, thereby resolving the catastrophic hypothesis collapse.