PUBO Formulation for MST and Application to Optimum-Path Forest
Guilherme E. L. Pexe, Lucas A. M. Rattighieri, Leandro A. Passos, Danilo S. Jodas, Douglas Rodrigues, Felipe F. Fanchini, João P. Papa, Kelton A. P. Costa
quant-phSubmitted May 20, 2026• Announced May 21, 2026• 0 citations• Revised Jun 2, 2026 (v2)
The Optimum-Path Forest is a graph-based framework for designing classifiers that exploit inter-sample connectivity. A particular variant constructs decision boundaries based on prototypes computed by a Minimum Spanning Tree (MST) over the training data, which might become prohibitive for large-scale datasets. In this context, Quantum Machine Learning has emerged as a promising approach to overcome the high computational burden of combinatorial problems. We propose a quantum-inspired approach for prototype selection in OPF classifiers by reformulating the MST problem as a Polynomial Unconstrained Binary Optimization (PUBO) task and further employing the Feedback-Based Quantum Optimization (FALQON) algorithm for Hamiltonian minimization. The PUBO formulation reduces the need for qubits and eliminates the need for auxiliary variables, thereby addressing scalability constraints in current quantum hardware. Experiments on real-world datasets demonstrate that the FALQON-optimized MST achieves accuracies comparable to those of the classical Prim's algorithm while maintaining prototype quality. While FALQON occasionally reached local minima, it did not significantly impact the accuracy of the prototype selection process.
The Optimum-Path Forest is a graph-based framework for designing classifiers that exploit inter-sample connectivity. A particular variant constructs decision boundaries based on prototypes computed by a Minimum Spanning Tree (MST) over the training data, which might become prohibitive for large-scale datasets. In this context, Quantum Machine Learning has emerged as a promising approach to overcome the high computational burden of combinatorial problems. We propose a quantum-inspired approach for prototype selection in OPF classifiers by reformulating the MST problem as a Polynomial Unconstrained Binary Optimization (PUBO) task and further employing the Feedback-Based Quantum Optimization (FALQON) algorithm for Hamiltonian minimization. The PUBO formulation reduces the need for qubits and eliminates the need for auxiliary variables, thereby addressing scalability constraints in current quantum hardware. Experiments on real-world datasets demonstrate that the FALQON-optimized MST achieves accuracies comparable to those of the classical Prim's algorithm while maintaining prototype quality. While FALQON occasionally reached local minima, it did not significantly impact the accuracy of the prototype selection process.
Finding the minimum spanning tree (MST) of a graph is an important task in computer vision, as it enables a sparse and low-cost representation of connectivity among elements (such as superpixels, points, or regions), which is useful for tasks such as segmentation, reconstruction, and clustering. In this work, we propose and evaluate a fully quantum pipeline for computing MSTs using the FALQON algorithm, a feedback-based quantum optimization method that does not require classical optimizers. We construct a Hamiltonian formulation whose ground-state energy encodes the MST of a graph and compare different FALQON strategies: (i) time rescaling (TR-FALQON) and (ii) multi-driver configurations. To avoid domain-specific biases, we adopt graphs with random weights and show that the FALQON variants exhibit significant differences in ground-state fidelity. We discuss the relevance of this approach for computer vision problems that naturally yield graph representations, and experimental results on synthetic instances together with a small demonstrative study on image segmentation illustrate both the potential and the current limitations of the method. Our numerical simulations on randomly weighted graphs show that standard one drive FALQON, although it reduces the expected energy, fails to concentrate amplitude in the MST solution. The multi drive variant succeeds in redistributing probability mass toward the ground state so that the MST appears among the most probable outcomes, and TR FALQON applied over multi drive produces the best results with faster convergence, lower final energy, and the highest solution state probability or fidelity in our tested instances. These improvements were observed on small synthetic graphs, underscoring both the promise of multi drive controls with temporal rescaling and the need for further scaling and hardware validation.
Quantum optimization algorithms, particularly the Quantum Approximate Optimization Algorithm (QAOA), have significantly addressed combinatorial optimization problems. While QAOA has been applied to various NP-hard problems, such as Max-Cut and the Traveling Salesman Problem (TSP), its application to the Degree-Constrained Minimum Spanning Tree (DCMST) problem remains unexplored. Inspired by Fowler’s formulation, this work presents the first implementation of the DCMST Hamiltonian within QAOA and insights from its benefits to graph-based machine learning algorithms. We investigated two approaches: (i) the standard QAOA ansatz with an X mixer and (ii) a warm-started QAOA utilizing classical preprocessing to enhance convergence. We used these strategies to provide numerical results for instances with 3 and 4 nodes, employing the COBYLA optimizer and metaheuristic optimization techniques. Our findings serve as a proof of concept, demonstrating the feasibility of applying QAOA to this problem; however, the number of qubits scales as O(N2) with the number of nodes, limiting scalability. Current research focuses on developing more efficient implementations that encode the same number of binary variables using fewer qubits. This study contributes to the expanding field of quantum optimization, highlighting the potential of hybrid quantum-classical algorithms, especially with resource-efficient mixers and warm-starting techniques, to solve complex combinatorial problems and advance the development of scalable quantum algorithms.
The superposition principle in quantum mechanics enables the encoding of an entire solution space within a single quantum state. By employing quantum routines such as amplitude amplification or the Quantum Approximate Optimization Algorithm (QAOA), this solution space can be explored in a computationally efficient manner to identify optimal or near-optimal solutions. In this article, we propose quantum circuits that operate on binary data representations to address a central task in prototype-based classification and representation learning, namely the so-called winner determination, which realizes the nearest prototype principle. We investigate quantum search algorithms to identify the closest prototype during prediction, as well as quantum optimization schemes for prototype selection in the training phase. For these algorithms, we design oracles based on arithmetic circuits that leverage quantum parallelism to apply mathematical operations simultaneously to multiple inputs. Furthermore, we introduce an oracle for prototype selection, integrated into a learning routine, which obviates the need for formulating the task as a binary optimization problem and thereby reduces the number of required auxiliary variables. All proposed oracles are implemented using the Python 3-based quantum machine learning framework PennyLane and empirically validated on synthetic benchmark datasets.
Abstract Quantum annealing aims at solving optimization problems of practical relevance using quantum-computing hardware. Problems of interest are typically formulated in terms of quadratic unconstrained binary optimization (QUBO) Hamiltonians. However, many optimization problems are much more naturally formulated in terms of polynomial unconstrained binary optimization (PUBO) functions of higher order. As we show with various problem examples, leveraging the PUBO formulation can bring considerable savings in terms of required number of qubits. Moreover, in numerical benchmarks for the paradigmatic 3-SAT problem, we find scenarios where the scaling of the minimum energy gap during the optimization sweep differs significantly, suggesting the possibility of an exponentially faster annealing time when using the PUBO as compared to the QUBO formulation. This advantage persists even when considering the overhead caused by the higher-order interactions necessary for PUBO cost Hamiltonians. As an interesting side effect, the analysis on minimum energy gaps of different 3-SAT instance generators reveals different degrees of hardness, which will be of interest also for classical benchmark calculations. Our findings show a promising path to improving the resource efficiency and sweeping speed of quantum annealing protocols on both analog and digital platforms, which are important prerequisites when aiming at solving larger optimization problems with relevance to industry.
Quantum Approximate Optimization Algorithm (QAOA) is one of the most short-term promising quantum-classical algorithm to solve unconstrained combinatorial optimization problems. It alternates between the execution of a parametrized quantum circuit and a classical optimization. There are numerous levers for enhancing QAOA performances, such as the choice of quantum circuit meta-parameters or the choice of the classical optimizer. In this paper, we stress on the importance of the input problem formulation by illustrating it with the resolution of an industrial railway timetabling problem. Specifically, we present a generic method to reformulate any polynomial problem into a Polynomial Unconstrained Binary Optimization (PUBO) problem, with a specific formulation imposing penalty terms to take binary values when the constraints are linear. We also provide a generic reformulation into a Quadratic Unconstrained Binary Optimization (QUBO) problem. We then conduct a numerical comparison between the PUBO with binary penalty terms and the QUBO formulations proposed on a railway timetabling problem solved with QAOA. Our results illustrate that the PUBO reformulation outperforms the QUBO one for the problem at hand.
As the volume of data for classification tasks in machine learning grows, feature selection plays an increasingly crucial role in enhancing the efficiency and effectiveness of these tasks. Existing classical feature selection algorithms often encounter challenges, such as high computational complexity and vulnerability to local optima. Quantum algorithms have been proposed to overcome these limitations. Here, our work proposes a new approach that combines the Quantum Approximate Optimization Algorithm (QAOA) with the classical feature selection algorithm Maximum Relevance-Minimum Redundancy (MRMR). First, we transform the feature selection problem into the Quadratic Unconstrained Binary Optimization (QUBO) problem. Then, we map the QUBO formulation to Hamiltonian with the Ising model. Finally, we employ QAOA with a shallow circuit to search this Hamiltonian's ground state, which matches the specific solution for feature selection. We conducted numerical experiments on eight real-world datasets for classification tasks from diverse domains, including finance, medicine, and natural hazards. Experiment results suggest that QAOA-selected feature subsets size are typically less than half the complete set while achieving comparable or better classification accuracy than classical MRMR, demonstrating its preference for smaller, more efficient feature subsets.