For any function computable by an optimal decision tree with size s, max depth D_opt and average depth Δ_opt, the greedy heuristic builds an ε-approximating tree of size at most exp(Δ_opt D_opt log(e/ε)) under arbitrary product distributions.
Theoretical Computer Science , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Linear decision trees can represent optimal solution policies for families of integer linear programs, enabling polynomial-time queries after offline synthesis for fixed feasible sets.
citing papers explorer
-
Decision Tree Learning on Product Spaces
For any function computable by an optimal decision tree with size s, max depth D_opt and average depth Δ_opt, the greedy heuristic builds an ε-approximating tree of size at most exp(Δ_opt D_opt log(e/ε)) under arbitrary product distributions.
-
Linear Decision Tree Policies for Integer Linear Programs
Linear decision trees can represent optimal solution policies for families of integer linear programs, enabling polynomial-time queries after offline synthesis for fixed feasible sets.