用逆优化+JKO框架学习群体演化，无需特殊网络结构。
Learning of Population Dynamics: Inverse Optimization Meets JKO Scheme
- 将逆优化融入JKO框架，端到端训练无须输入凸神经网络
- 在多个数据集上优于现有基于JKO的方法，提升明显
- 适合研究粒子演化建模与概率空间优化的科研人员
学习群体动态旨在根据离散时间点的样本快照，还原驱动粒子演化的底层过程。近期方法将此问题建模为概率空间中的能量最小化，并利用著名的JKO方案实现高效的时间离散化。本文提出$ exttt{iJKOnet}$，结合JKO框架与逆优化技术以学习群体动态。该方法采用常规的端到端对抗训练流程，无需限制性网络结构（如输入凸神经网络）。我们为该方法建立了理论保证，并在实验中展示了其相较于先前基于JKO方法的显著性能提升。$ exttt{iJKOnet}$的代码已开源于https://github.com/MuXauJl11110/iJKOnet。
原文摘要 · Abstract (English)
Learning population dynamics involves recovering the underlying process that governs particle evolution, given evolutionary snapshots of samples at discrete time points. Recent methods frame this as an energy minimization problem in probability space and leverage the celebrated JKO scheme for efficient time discretization. In this work, we introduce $\texttt{iJKOnet}$, an approach that combines the JKO framework with inverse optimization techniques to learn population dynamics. Our method relies on a conventional $\textit{end-to-end}$ adversarial training procedure and does not require restrictive architectural choices, e.g., input-convex neural networks. We establish theoretical guarantees for our methodology and demonstrate improved performance over prior JKO-based methods. The code of $\texttt{iJKOnet}$ is available at https://github.com/MuXauJl11110/iJKOnet.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。