Trees to Flows and Back: Unifying Decision Trees and Diffusion Models

MCML Authors

Sai Niranjan Ramachandran

→ Group Suvrit Sra
 Resource Aware Machine Learning

Suvrit Sra

Prof. Dr.

Core PI

Resource Aware Machine Learning

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: emph{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× computational speedup, and dsmtree, a novel distillation method that transfers hierarchical decision logic into neural networks, matching teacher performance within 2% on many benchmarks.

inproceedings RS26

---

ICML 2026

43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available.

---

Authors

S. N. Ramachandran • S. Sra

---

Links

URL

---

Research Area

 A2 | Mathematical Foundations