Predict-then-Optimize for Seaport Power-Logistics Scheduling: Generalization across Varying Tasks Stream
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914155744722944 |
|---|---|
| author | Pu, Chuanqing Fan, Feilong Tai, Nengling Xu, Yan Huang, Wentao Wen, Honglin |
| author_facet | Pu, Chuanqing Fan, Feilong Tai, Nengling Xu, Yan Huang, Wentao Wen, Honglin |
| contents | Power-logistics scheduling in modern seaports typically follow a predict-then-optimize pipeline. To enhance the decision quality of forecasts, decision-focused learning has been proposed, which aligns the training of forecasting models with downstream decision outcomes. However, this end-to-end design inherently restricts the value of forecasting models to only a specific task structure, and thus generalize poorly to evolving tasks induced by varying seaport vessel arrivals. We address this gap with a decision-focused continual learning framework that adapts online to a stream of scheduling tasks. Specifically, we introduce Fisher information based regularization to enhance cross-task generalization by preserving parameters critical to prior tasks. A differentiable convex surrogate is also developed to stabilize gradient backpropagation. The proposed approach enables learning a decision-aligned forecasting model across a varying tasks stream with a sustainable long-term computational burden. Experiments calibrated to the Jurong Port demonstrate superior decision performance and generalization over existing methods with reduced computational cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_07938 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Predict-then-Optimize for Seaport Power-Logistics Scheduling: Generalization across Varying Tasks Stream Pu, Chuanqing Fan, Feilong Tai, Nengling Xu, Yan Huang, Wentao Wen, Honglin Machine Learning Systems and Control Power-logistics scheduling in modern seaports typically follow a predict-then-optimize pipeline. To enhance the decision quality of forecasts, decision-focused learning has been proposed, which aligns the training of forecasting models with downstream decision outcomes. However, this end-to-end design inherently restricts the value of forecasting models to only a specific task structure, and thus generalize poorly to evolving tasks induced by varying seaport vessel arrivals. We address this gap with a decision-focused continual learning framework that adapts online to a stream of scheduling tasks. Specifically, we introduce Fisher information based regularization to enhance cross-task generalization by preserving parameters critical to prior tasks. A differentiable convex surrogate is also developed to stabilize gradient backpropagation. The proposed approach enables learning a decision-aligned forecasting model across a varying tasks stream with a sustainable long-term computational burden. Experiments calibrated to the Jurong Port demonstrate superior decision performance and generalization over existing methods with reduced computational cost. |
| title | Predict-then-Optimize for Seaport Power-Logistics Scheduling: Generalization across Varying Tasks Stream |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2511.07938 |