Metraipolis › archive › dc_34836bb77b16
TracingFlow: A Simulation-Free Trajectory Inference Framework Based on Second-Order Dynamics — arXiv:2608.21070
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.21070
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T10:31:10.944Z
- SHA-256 of the archived text
7df20af71aff52d1f309e36c0c84429d089962e35fdbb3a4db8b37113105a894- Stable URL of this page
https://metraipolis.com/documento/dc_34836bb77b16
How to cite
TracingFlow: A Simulation-Free Trajectory Inference Framework Based on Second-Order Dynamics — arXiv:2608.21070 — arXiv (en), https://arxiv.org/abs/2608.21070 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_34836bb77b16 (Metraipolis archive dc_34836bb77b16, sha256 7df20af71aff52d1f309e36c0c84429d089962e35fdbb3a4db8b37113105a894)
BibTeX
@misc{dc34836bb77b16,
title = {TracingFlow: A Simulation-Free Trajectory Inference Framework Based on Second-Order Dynamics — arXiv:2608.21070},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.21070},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_34836bb77b16; sha256 7df20af71aff52d1f309e36c0c84429d089962e35fdbb3a4db8b37113105a894},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21070. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Inferring continuous system evolution from sparse temporal snapshots is a key challenge in generative modeling and single-cell omics. While Optimal Transport (OT) is popular, existing frameworks are largely restricted to first-order dynamics, assuming memoryless velocity fields. This limits expressiveness, as first-order systems fail to account for regulatory momentum and time-delayed responses inherent in processes like cell differentiation. Here, we introduce TracingFlow, a simulation-free Flow Matching framework generalizing to second-order dynamics. By using neural networks to regress the acceleration field, TracingFlow provides an exact, efficient solution to the Dynamical Optimal Acceleration Transport (DOAT) problem. Unlike first-order methods yielding over-smoothed trajectories, our second-order formulation captures high-curvature transitions and nonlinear evolutions by learning the underlying force fields. Evaluated on complex synthetic and large-scale scRNA-seq datasets, TracingFlow achieves superior accuracy in distributional reconstruction and trajectory faithfulness. Moreover, by integrating lineage tracing priors, it recovers dynamical structures that are both mathematically optimal and biologically plausible. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Genomics (q-bio.GN). Pagina del lavoro: https://arxiv.org/abs/2608.21070 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T10:27:55.951Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).