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

arXiv:2605.00414v1 Announce Type: new 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: reeflow, which achieves competitive generation quality on tabular data with higher fidelity and a 2imes computational speedup, and smtree, a novel distillation method that transfers hierarchical decision logic into neural networks, matching teacher performance within 2% on many benchmarks.

Source: arXiv cs.LG | 2026-05-04