arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.04675cs.LG
收藏

图上的广义薛定谔桥

Generalized Schrödinger Bridge on Graphs

University of California, Berkeley(加州大学伯克利分校)

Panagiotis Theodoropoulos, Juno Nam, Evangelos Theodorou, Jaemoo Choi

AI总结:

提出GSBoG框架,通过似然优化学习图上可控连续时间马尔可夫链策略,满足端点边际分布并优化中间状态成本,实现可扩展的拓扑感知运输。

摘要:

图上的运输是许多领域中的一个基本挑战,决策必须尊重拓扑和操作约束。尽管需要可执行的策略,现有的图运输方法缺乏这种表达能力。它们依赖于限制性假设,无法在稀疏拓扑上泛化,并且随着图大小和时间范围的增加而扩展性差。为了解决这些问题,我们引入了图上的广义薛定谔桥(GSBoG),这是一种新颖的可扩展数据驱动框架,用于在状态成本增强动力学下学习任意图上的可执行受控连续时间马尔可夫链(CTMC)策略。值得注意的是,GSBoG学习轨迹级策略,避免了密集的全局求解器,从而增强了可扩展性。这是通过似然优化方法实现的,满足端点边际分布,同时优化状态依赖运行成本下的中间行为。在具有挑战性的真实世界图拓扑上的大量实验表明,GSBoG能够可靠地学习准确、尊重拓扑的策略,同时优化特定应用的中间状态成本,突出了其广泛的适用性,并为一般图上的成本感知动态运输开辟了新途径。

英文摘要:

Transportation on graphs is a fundamental challenge across many domains, where decisions must respect topological and operational constraints. Despite the need for actionable policies, existing graph-transport methods lack this expressivity. They rely on restrictive assumptions, fail to generalize across sparse topologies, and scale poorly with graph size and time horizon. To address these issues, we introduce Generalized Schrödinger Bridge on Graphs (GSBoG), a novel scalable data-driven framework for learning executable controlled continuous-time Markov chain (CTMC) policies on arbitrary graphs under state cost augmented dynamics. Notably, GSBoG learns trajectory-level policies, avoiding dense global solvers and thereby enhancing scalability. This is achieved via a likelihood optimization approach, satisfying the endpoint marginals, while simultaneously optimizing intermediate behavior under state-dependent running costs. Extensive experimentation on challenging real-world graph topologies shows that GSBoG reliably learns accurate, topology-respecting policies while optimizing application-specific intermediate state costs, highlighting its broad applicability and paving new avenues for cost-aware dynamical transport on general graphs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑