Saved in:
Bibliographic Details
Main Authors: Sun, He, Shin, Jiwoong, Dhar, Ravi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.01663
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918271887867904
author Sun, He
Shin, Jiwoong
Dhar, Ravi
author_facet Sun, He
Shin, Jiwoong
Dhar, Ravi
contents We study generative modeling of \emph{variable-length trajectories} -- sequences of visited locations/items with associated timestamps -- for downstream simulation and counterfactual analysis. A recurring practical issue is that standard mini-batch training can be unstable when trajectory lengths are highly heterogeneous, which in turn degrades \emph{distribution matching} for trajectory-derived statistics. We propose \textbf{length-aware sampling (LAS)}, a simple batching strategy that groups trajectories by length and samples batches from a single length bucket, reducing within-batch length heterogeneity (and making updates more consistent) without changing the model class. We integrate LAS into a conditional trajectory GAN with auxiliary time-alignment losses and provide (i) a distribution-level guarantee for derived variables under mild boundedness assumptions, and (ii) an IPM/Wasserstein mechanism explaining why LAS improves distribution matching by removing length-only shortcut critics and targeting within-bucket discrepancies. Empirically, LAS consistently improves matching of derived-variable distributions on a multi-mall dataset of shopper trajectories and on diverse public sequence datasets (GPS, education, e-commerce, and movies), outperforming random sampling across dataset-specific metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2601_01663
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Length-Aware Adversarial Training for Variable-Length Trajectories: Digital Twins for Mall Shopper Paths
Sun, He
Shin, Jiwoong
Dhar, Ravi
Machine Learning
Artificial Intelligence
We study generative modeling of \emph{variable-length trajectories} -- sequences of visited locations/items with associated timestamps -- for downstream simulation and counterfactual analysis. A recurring practical issue is that standard mini-batch training can be unstable when trajectory lengths are highly heterogeneous, which in turn degrades \emph{distribution matching} for trajectory-derived statistics. We propose \textbf{length-aware sampling (LAS)}, a simple batching strategy that groups trajectories by length and samples batches from a single length bucket, reducing within-batch length heterogeneity (and making updates more consistent) without changing the model class. We integrate LAS into a conditional trajectory GAN with auxiliary time-alignment losses and provide (i) a distribution-level guarantee for derived variables under mild boundedness assumptions, and (ii) an IPM/Wasserstein mechanism explaining why LAS improves distribution matching by removing length-only shortcut critics and targeting within-bucket discrepancies. Empirically, LAS consistently improves matching of derived-variable distributions on a multi-mall dataset of shopper trajectories and on diverse public sequence datasets (GPS, education, e-commerce, and movies), outperforming random sampling across dataset-specific metrics.
title Length-Aware Adversarial Training for Variable-Length Trajectories: Digital Twins for Mall Shopper Paths
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2601.01663