TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecasting
This addresses the trade-off between accuracy, efficiency, and stability in probabilistic forecasting for decision-making applications, representing a strong specific gain rather than a foundational advance.
The paper tackled the problem of training instability and hypothesis collapse in efficient non-sampling probabilistic time-series forecasting models, particularly when combined with MLP-based backbones, by proposing TimePre with Stabilized Instance Normalization, achieving state-of-the-art accuracy on six benchmarks and orders-of-magnitude faster inference speeds than sampling-based models.
Probabilistic Time-Series Forecasting (PTSF) is critical for uncertainty-aware decision making, but existing generative models, such as diffusion-based approaches, are computationally prohibitive due to expensive iterative sampling. Non-sampling frameworks like Multiple Choice Learning (MCL) offer an efficient alternative, but suffer from severe training instability and hypothesis collapse, which has historically hindered their performance. This problem is dramatically exacerbated when attempting to combine them with modern, efficient MLP-based backbones. To resolve this fundamental incompatibility, we propose TimePre, a novel framework that successfully unifies the efficiency of MLP-based models with the distributional flexibility of the MCL paradigm. The core of our solution is Stabilized Instance Normalization (SIN), a novel normalization layer that explicitly remedies this incompatibility. SIN stabilizes the hybrid architecture by correcting channel-wise statistical shifts, definitively resolving the catastrophic hypothesis collapse. Extensive experiments on six benchmark datasets demonstrate that TimePre achieves new state-of-the-art accuracy on key probabilistic metrics. Critically, TimePre achieves inference speeds orders of magnitude faster than sampling-based models and, unlike prior MCL work, demonstrates stable performance scaling. It thus bridges the long-standing gap between accuracy, efficiency, and stability in probabilistic forecasting.