arXiv：cs.LG（机器学习，全量分类）· Mahindra Rautela, Alexander Scheinker, Ayan Biswas, Diane Oyen, Nathan DeBardeleben, Earl Lawrence·· 17 小时前AI 评分31
Sim+Real：联合仿真-实验训练提升物理系统预测的均衡性
Sim+Real: Joint Simulation - Experiment Training Improves Balanced Prediction in Physical Systems
AI 导读
研究将仿真-实验预测建模为多目标学习问题，在 RealPDEBench 的四个流体系统和两种模型容量上对比了仅仿真、仅实验、Sim→Exp 和联合训练四种方式。Sim→Exp 会偏向实验数据并导致仿真域遗忘，而联合训练在广泛的仿真-实验评估权重下持续取得最佳均衡性能，并显著提升仿真保留能力。
正文
Abstract:Simulation and experimental measurements provide complementary data for learning spatiotemporal physical systems, but standard simulation-to-experiment fine-tuning optimizes only the experimental objective after transfer and can degrade simulation performance. We formulate simulation--experiment prediction as a multi-objective learning problem with domain-specific simulation and experimental risks. On four fluid systems from RealPDEBench and two model capacities, we compare Simulation only, Experiment only, Sim$\rightarrow$Exp, and Joint training, evaluating every final model on both held-out domains. Sim$\rightarrow$Exp tends to specialize more strongly to experimental data at the cost of simulation-domain forgetting. Joint training consistently achieves the best balanced performance over a broad range of simulation--experiment evaluation weightings, while substantially improving simulation retention over Sim$\rightarrow$Exp. Joint also better preserves simulation-only fields absent from experimental measurements. Project page: this https URL.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.01974 [cs.LG] |
| (or arXiv:2610.01974v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.01974 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mahindra Rautela [view email]
[v1]
Thu, 1 Oct 2026 16:22:46 UTC (2,157 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org