跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.26044 · v1

Variational Trajectory Flow Matching with a Non-Linear Interpolant

首次提交 2026-11-19 20:53
版本更新 2026-11-19 20:53
雷达观测 2026-11-20 16:53
arXiv ↗PDF ↗

摘要

Simulation-free methods such as Trajectory Flow Matching learn dynamics by regressing the time derivative of a local interpolant placed between consecutive observations. The interpolant defines the regression target, and under sparse, irregular sampling, it underrepresents the dynamics and bounds what can be learned. We show that no fixed interpolant dominates: the best of linear, quadratic, spline and quintic changes with the system and with the sampling density. We propose to learn the interpolant instead. An amortized implicit neural representation (INR) is fitted to the training trajectories and frozen as a teacher supplying the target velocity to a learnable velocity field. We further frame the velocity field within a variational framework, yielding a probabilistic forecaster that, at inference, requires only the velocity field and no SDE solver. We evaluate our method on a range of dynamical systems: it consistently achieves high accuracy and more stable long-horizon rollouts under sparser observations, at matched velocity-field capacity.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-19 20:53 · 最新观测版本

Variational Trajectory Flow Matching with a Non-Linear Interpolant

Simulation-free methods such as Trajectory Flow Matching learn dynamics by regressing the time derivative of a local interpolant placed between consecutive observations. The interpolant defines the regression target, and under sparse, irregular sampling, it underrepresents the dynamics and bounds what can be learned. We show that no fixed interpolant dominates: the best of linear, quadratic, spline and quintic changes with the system and with the sampling density. We propose to learn the interpolant instead. An amortized implicit neural representation (INR) is fitted to the training trajectories and frozen as a teacher supplying the target velocity to a learnable velocity field. We further frame the velocity field within a variational framework, yielding a probabilistic forecaster that, at inference, requires only the velocity field and no SDE solver. We evaluate our method on a range of dynamical systems: it consistently achieves high accuracy and more stable long-horizon rollouts under sparser observations, at matched velocity-field capacity.

查看此版本解读 →查看此版本原文 ↗