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.
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
For functions with optimal decision tree of size s, max depth D_opt and avg depth Δ_opt, greedy builds an ε-approximating tree of size at most exp(Δ_opt D_opt log(e/ε)) under product distributions.
citing papers explorer
-
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.
-
Decision Tree Learning on Product Spaces
For functions with optimal decision tree of size s, max depth D_opt and avg depth Δ_opt, greedy builds an ε-approximating tree of size at most exp(Δ_opt D_opt log(e/ε)) under product distributions.