QUBO Decision Tree: Annealing Machine Extends Decision Tree Splitting
arXiv:2303.09772 · doi:10.1109/ICKG55886.2022.00052
Abstract
This paper proposes an extension of regression trees by quadratic unconstrained binary optimization (QUBO). Regression trees are very popular prediction models that are trainable with tabular datasets, but their accuracy is insufficient because the decision rules are too simple. The proposed method extends the decision rules in decision trees to multi-dimensional boundaries. Such an extension is generally unimplementable because of computational limitations, however, the proposed method transforms the training process to QUBO, which enables an annealing machine to solve this problem.
arXiv comment2022 IEEE International Conference on Knowledge Graph (ICKG)
References in corpus (12)
- XGBoost: A Scalable Tree Boosting System
- Quantum Annealing in the Transverse Ising Model
- A Quantum Adiabatic Evolution Algorithm Applied to Random Instances of an NP-Complete Problem
- Quantum Optimization of Fully-Connected Spin Glasses
- Quantum annealing of the Traveling Salesman Problem
- A Tutorial on Formulating and Using QUBO Models
- Quantum Annealing Applied to De-Conflicting Optimal Trajectories for Air Traffic Management
- Bayesian Network Structure Learning Using Quantum Annealing
- How "Quantum" is the D-Wave Machine?
- Performance of a Quantum Annealer for Ising Ground State Computations on Chimera Graphs
- Quantum Annealing for Clustering
- Quadratic unconstrained binary optimization formulation for rectified-linear-unit-type functions