研究人员引入了 Wasserstein 拉格朗日力学（WLM），一个用于模拟群体动力学的新颖框架。与之前最小化自由能的方法不同，WLM 最小化群体层面的作用量，使其能够捕捉周期性等特性。所提出的 WLM 算法可以直接从观测数据中学习这些二阶动力学，并在各种应用中预测和插值未见动力学方面表现出优于现有方法的性能。 AI
影响 引入了一个新的算法框架来学习复杂动力学，有可能改进科学建模中的预测和插值。
排序理由 详细介绍新算法方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.08550v2 Announce Type: replace-cross Abstract: The population dynamics of molecules, cells, and organisms are governed by a number of unknown forces. In the last decade, population dynamics have predominantly been modeled with Wasserstein gradient flows. However, since…
The population dynamics of molecules, cells, and organisms are governed by a number of unknown forces. In the last decade, population dynamics have predominantly been modeled with Wasserstein gradient flows. However, since gradient flows minimize free energy, they fail to capture…