Saved in:
Bibliographic Details
Main Authors: Zweig, Aaron, Zhang, Mingxuan, Knowles, David A., Azizi, Elham
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.16708
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910056376696832
author Zweig, Aaron
Zhang, Mingxuan
Knowles, David A.
Azizi, Elham
author_facet Zweig, Aaron
Zhang, Mingxuan
Knowles, David A.
Azizi, Elham
contents Trajectory inference investigates how to interpolate paths between observed timepoints of dynamical systems, such as temporally resolved population distributions, with the goal of inferring trajectories at unseen times and better understanding system dynamics. Previous work has focused on continuous geometric priors, utilizing data-dependent spatial features to define a Riemannian metric. In many applications, there exists discrete, directed prior knowledge over admissible transitions (e.g. lineage trees in developmental biology). We introduce a Finsler metric that combines geometry with classification and incorporate both types of priors in trajectory inference, yielding improved performance on interpolation tasks in synthetic and real-world data.
format Preprint
id arxiv_https___arxiv_org_abs_2603_16708
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning Lineage-guided Geodesics with Finsler Geometry
Zweig, Aaron
Zhang, Mingxuan
Knowles, David A.
Azizi, Elham
Machine Learning
Trajectory inference investigates how to interpolate paths between observed timepoints of dynamical systems, such as temporally resolved population distributions, with the goal of inferring trajectories at unseen times and better understanding system dynamics. Previous work has focused on continuous geometric priors, utilizing data-dependent spatial features to define a Riemannian metric. In many applications, there exists discrete, directed prior knowledge over admissible transitions (e.g. lineage trees in developmental biology). We introduce a Finsler metric that combines geometry with classification and incorporate both types of priors in trajectory inference, yielding improved performance on interpolation tasks in synthetic and real-world data.
title Learning Lineage-guided Geodesics with Finsler Geometry
topic Machine Learning
url https://arxiv.org/abs/2603.16708