Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models

arXiv:2511.00053v2 Announce Type: replace-cross Abstract: The design of learning objectives is central to training time-series forecasting models. Existing learning objectives such as mean squared error mostly treat each future step as an independent, equally weighted task, which leads to the following two challenges: (1) they overlook the label autocorrelation effect among future steps, leading to biased learning objectives; (2) they fail to set heterogeneous task weights for different forecasting tasks corresponding to varying future steps, limiting the forecasting performance. To fill this gap, we propose a novel quadratic-form weighted learning objective, addressing both issues simultaneously. Specifically, the off-diagonal elements of the weighting matrix account for the label autocorrelation effect, whereas the non-uniform diagonals are expected to match the preferred weights of the forecasting tasks with varying future steps. On this basis, we propose a Quadratic Direct Forecast (QDF) learning algorithm, which trains the forecast model using the adaptively updated quadratic-form weighting matrix. Experiments show that our QDF effectively improves the performance of various forecast models, achieving state-of-the-art results. Code is available at https://github.com/Master-PLC/QDF.

Related

• Weighted Contrastive Learning for Anomaly-Aware Time-Series Forecasting
• Beyond MSE: Improving Precipitation Nowcasting with Multi-Quantile Regression
• Time-o1: Time-Series Forecasting Needs Transformed Label Alignment
• Reasoning-Aware Training for Time Series Forecasting

Source: arXiv cs.AI | 2026-10-07