arXiv cs.AI· Zihan Wang, Jianzhe Li, Zhenyi Zhang, Peijie Zhou·· 10 小时前AI 评分31
Elysium:免模拟的非平衡薛定谔桥求解器
Elysium: Simulation-Free Unbalanced Schr\"odinger Bridges
AI 导读
Elysium 是一种免模拟的非平衡薛定谔桥求解器,联合学习状态转移与质量变化,训练时无需模拟轨迹。它基于 killed Brownian 参考过程及其时间反演,从最优端点耦合与条件桥分布构造直接回归目标,并证明训练目标的最小化解可恢复最优非平衡薛定谔桥。
正文 · 原文
Abstract:Reconstructing cellular dynamics from snapshots is challenging because the destructive nature of single-cell measurements makes tracking the same cells over time impossible. Cellular dynamics are inherently stochastic and involve changes in population size through proliferation and apoptosis. Growth-based methods represent population change as a rate on the density, which does not assign exits and entries to individual cells. Unbalanced Schrödinger bridges model individual events, but neural solvers for killed diffusion bridges simulate trajectories during training. We introduce Elysium, a simulation-free solver that jointly learns state transition and mass change. Using a killed Brownian reference and its time reversal, Elysium constructs direct regression objectives from an optimal endpoint coupling and conditional bridge distributions, without simulating trajectories during training. We show that the minimizers of the expected training objectives recover the optimal unbalanced Schrödinger bridge. Empirically, Elysium reconstructs state transitions, population size, and event distributions on simulated benchmarks with known killed-diffusion ground truth, outperforming existing deterministic and bridge-based solvers. On single-cell time courses, it interpolates cell state distributions at unobserved time points, tracks population expansion and contraction, and captures biphasic drug-response dynamics.
| Comments: | 44 pages, 9 figures |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM) |
| Cite as: | arXiv:2611.24763 [cs.LG] |
| (or arXiv:2611.24763v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.24763 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zihan Wang [view email]
[v1]
Wed, 18 Nov 2026 17:16:41 UTC (1,132 KB)
来源:arXiv cs.AI · arxiv.org