arXiv cs.AI· Jinyu Zhang, Di Huang, Zhiyuan Liu, Nikolas Geroliminis·· 4 小时前AI 评分23
多阶段上下文优化用于网约车车辆调度
Multistage Contextual Optimization for Vehicle Repositioning
AI 导读
研究提出多阶段上下文优化方法,用决策表现训练预测模型,并推导出包含三部分的精确梯度,配合伴随反向传播避免求解完整雅可比矩阵。在纽约市网约车数据上,该方法比用均方误差训练的同一预测器多带来 7.7% 至 9.1% 的业务收益,优于五个范式的所有对比基线,甚至超过将真实需求喂给同一策略的效果。八核并行块评估将训练时间缩短 1.86 倍且不损失决策表现。
正文 · 原文
Abstract:Ride-hailing platforms reposition idle vehicles to improve spatial supply-demand balances. This problem is prediction-driven and multistage: at each stage, the platform forecasts future demand, executes current decisions, and uses the resulting state to initialize the next stage. We formulate a multistage linear program (LP) with a macroscopic fundamental diagram (MFD) linking accumulation to trip completion. We then develop a multistage contextual optimization approach that uses decision performance to train the prediction model. The learning problem combines multiple coupled stages, context that depends on earlier decisions, and predictions that affect the objective, the constraint matrix, and the right-hand side of the LP. We derive the exact gradient, which has three parts: parameters change forecasts and hence decisions; earlier decisions change the current decision through the inherited state; and this state also changes forecasts as context. An equivalent adjoint uses reverse vector-Jacobian products, avoiding full solution and state-parameter Jacobians. Finally, forward propagation solves many stage LPs one after another, which makes training slow. We propose a parallel block evaluation algorithm that solves blocks of consecutive stages in parallel and repeatedly feeds each block output to the next block. We prove that the algorithm recovers the serial trajectory within a finite number of passes and that its gradient error remains bounded when it stops early. On New York City ride-hailing data, multistage contextual optimization yields 7.7% to 9.1% more business benefit than the same predictor trained by mean squared error, outperforms all compared baselines from five paradigms, and even outperforms realized demand fed to the same policy. With eight workers, parallel block evaluation shortens training by a factor of 1.86 without loss of decision performance.
| Comments: | 44 pages, 8 figures |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.22330 [cs.AI] |
| (or arXiv:2611.22330v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22330 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Di Huang [view email]
[v1]
Tue, 17 Nov 2026 07:27:54 UTC (6,661 KB)
来源:arXiv cs.AI · arxiv.org