| title | Trees to Flows and Back: Unifying Decision Trees and Diffusion Models |
|---|---|
| authors | Sai Niranjan Ramachandran, Suvrit Sra |
| date | 2026-05-01 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.00414 |
| affiliation | Technical University of Munich |
| upvotes | 7 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Decision trees and diffusion models are ostensibly disparate model classes, one discrete and hierarchical, the other continuous and dynamic. This work unifies the two by establishing a crisp mathematical correspondence between hierarchical decision trees and diffusion processes in appropriate limiting regimes. Our unification reveals a shared optimization principle: Global Trajectory Score Matching (GTSM), for which gradient boosting (in an idealized version) is asymptotically optimal. We underscore the conceptual value of our work through two key practical instantiations: \treeflow, which achieves competitive generation quality on tabular data with higher fidelity and a 2\times computational speedup, and \dsmtree, a novel distillation method that transfers hierarchical decision logic into neural networks, matching teacher performance within 2\% on many benchmarks. |
cite
@misc{ramachandran2026trees,
title={Trees to Flows and Back: Unifying Decision Trees and Diffusion Models},
author={Sai Niranjan Ramachandran and Suvrit Sra},
year={2026},
eprint={2605.00414},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.00414}
}