TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecasting

Abstract: We proposeTimePre, 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. Extensive experiments on six benchmark datasets demonstrate that TimePre achieves the best Distortion on all six benchmarks and the best or highly competitive CRPS-Sum on most benchmarks. Critically, TimePre achieves inference speeds that are orders of magnitude faster than sampling-based models, and is more stable than prior MCL approaches.

Submission Type: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Andres_R_Masegosa1

Submission Number: 8372