Abstract

Machine learning for wireless systems is commonly studied using standardized stochastic channel models (e.g., TDL/CDL/UMa) because of their legacy in wireless communication standardization and their ability to generate data at scale. However, some of their structural assumptions may diverge from real-world propagation. This paper asks when these models are sufficient and when ray-traced (RT) data — a proxy for the real world — provides tangible benefits. To answer these questions, we conduct an empirical study on two representative tasks: CSI compression and temporal channel prediction. Models are trained and evaluated using in-domain, cross-domain, and small-data fine-tuning protocols. Across settings, we observe that stochastic-only evaluation may over- or under-estimate performance relative to RT. These findings support a task-aware recipe where stochastic models can be leveraged for scalable pre-training and for tasks that do not rely on strong spatiotemporal coupling. When that coupling matters, pre-training and evaluation should be grounded in spatially consistent or geometrically similar RT scenarios. This study provides initial guidance to inform future discussions on benchmarking and standardization.

Figures

Note: Figures 1 and 2 in this paper are HTML diagrams/tables in the arXiv source — not raster images. They are not reproduced here. The PDF version on arXiv contains the full set.

Bibtex

@misc{morais2025comparingstochasticraytracing,
  title         = {Comparing Stochastic and Ray-tracing Datasets in Machine Learning for Wireless Applications},
  author        = {João Morais and Akshay Malhotra and Shahab Hamidi-Rad and Ahmed Alkhateeb},
  year          = {2025},
  eprint        = {2512.12449},
  archivePrefix = {arXiv},
  primaryClass  = {eess.SP},
  url           = {https://arxiv.org/abs/2512.12449}
}