Graph partitioning is one of an important set of well-known compute-intense (NP-hard) graph problems that devolve to discrete constrained optimization. We sampled solutions to the problem via two different quantum-ready methods to understand the strengths and weaknesses of each method. First we formulated and sampled the problem as a quadratic unconstrained binary optimization (QUBO) problem, via the best known QUBO formulation, using a best-in-class QUBO sampler running purely classically. Second, we formulated the problem at a higher level, as a set of constraints and an objective function, and sampled it with a recently developed constrained-optimization sampler (which generates QUBOs and also samples them classically). We find that both approaches often deliver better partitions than the purpose-built classical graph partitioners. Further, we find that the constrained-optimization approach is often able to deliver better partitions in less time than the bespoke-QUBO approach, without specific knowledge of the graph-partitioning problem. Stepping back from graph partitioning itself, one key question is whether bespoke algorithms for high-value problems or general tools for classes of problems are more likely to deliver the power of QCs to a broad market of real-world users. We believe this early evidence, though anecdotal, supports the proposition that general tools may contribute significant benefit to a range of problems, expanding the impact of QCs on industry and society. The fact that this benefit is independent of the low-level sampler employed, whether classical software or one of a variety of QC architectures, reinforces the need for further work on high-level optimization. The commercial availability in the cloud of such software today, delivering superior classical performance for some problems, enables quantum-forward organizations to migrate to quantum-ready methods now, accelerating progress toward quantum advantage and ensuring sampler software evolves to address the problems such organizations value.
Graph partitioning is one of an important set of well-known compute-intense (NP-hard) graph problems that devolve to discrete constrained optimization. We sampled solutions to the problem via two different quantum-ready methods to understand the strengths and weaknesses of each method. First we formulated and sampled the problem as a quadratic unconstrained binary optimization (QUBO) problem, via the best known QUBO formulation, using a best-in-class QUBO sampler running purely classically. Second, we formulated the problem at a higher level, as a set of constraints and an objective function, and sampled it with a recently developed constrained-optimization sampler (which generates QUBOs and also samples them classically). We find that both approaches often deliver better partitions than the purpose-built classical graph partitioners. Further, we find that the constrained-optimization approach is often able to deliver better partitions in less time than the bespoke-QUBO approach, without specific knowledge of the graph-partitioning problem. Stepping back from graph partitioning itself, one key question is whether bespoke algorithms for high-value problems or general tools for classes of problems are more likely to deliver the power of QCs to a broad market of real-world users. We believe this early evidence, though anecdotal, supports the proposition that general tools may contribute significant benefit to a range of problems, expanding the impact of QCs on industry and society. The fact that this benefit is independent of the low-level sampler employed, whether classical software or one of a variety of QC architectures, reinforces the need for further work on high-level optimization. The commercial availability in the cloud of such software today, delivering superior classical performance for some problems, enables quantum-forward organizations to migrate to quantum-ready methods now, accelerating progress toward quantum advantage and ensuring sampler software evolves to address the problems such organizations value.
Many organizations that vitally depend on computation for their competitive advantage are keen to exploit the expected performance of quantum computers (QCs) as soon as quantum advantage is achieved. The best approach to deliver hardware quantum advantage for high-value problems is not yet clear. This work advocates establishing quantum-ready applications and underlying tools and formulations, so that software development can proceed now to ensure being ready for quantum advantage. This work can be done independently of which hardware approach delivers quantum advantage first. The quadratic unconstrained binary optimization (QUBO) problem is one such quantum-ready formulation. We developed the next generation of qbsolv, a tool that is widely used for sampling QUBOs on early QCs, focusing on its performance executing purely classically, and deliver it as a cloud service today. We find that it delivers highly competitive results in all of quality (low energy value), speed (time to solution), and diversity (variety of solutions). We believe these results give quantum-forward users a reason to switch to quantum-ready formulations today, reaping immediate benefits in performance and diversity of solution from the quantum-ready formulation,preparing themselves for quantum advantage, and accelerating the development of the quantum computing ecosystem.
Quantum annealers offer an efficient way to compute high quality solutions of NP-hard problems when expressed in a QUBO (quadratic unconstrained binary optimization) or an Ising form. This is done by mapping a problem onto the physical qubits and couplers of the quantum chip, from which a solution is read after a process called quantum annealing. However, this process is subject to multiple sources of biases, including poor calibration, leakage between adjacent qubits, control biases, etc., which might negatively influence the quality of the annealing results. In this work, we aim at mitigating the effect of such biases for solving constrained optimization problems, by offering a two-step method, and apply it to Graph Partitioning. In the first step, we measure and reduce any biases that result from implementing the constraints of the problem. In the second, we add the objective function to the resulting bias-corrected implementation of the constraints, and send the problem to the quantum annealer. We apply this concept to Graph Partitioning, an important NP-hard problem, which asks to find a partition of the vertices of a graph that is balanced (the constraint) and minimizes the cut size (the objective). We first quantify the bias of the implementation of the constraint on the quantum annealer, that is, we require, in an unbiased implementation, that any two vertices have the same likelihood of being assigned to the same or to different parts of the partition. We then propose an iterative method to correct any such biases. We demonstrate that, after adding the objective, solving the resulting bias-corrected Ising problem on the quantum annealer results in a higher solution accuracy.
Quantum computing offers significant potential for solving NP-hard combinatorial (optimization) problems that are beyond the reach of classical computers. One way to tap into this potential is by reformulating combinatorial problems as a quadratic unconstrained binary optimization (QUBO) problem. The solution of the QUBO reformulation can then be addressed using adiabatic quantum computing devices or appropriate quantum computing algorithms on gate-based quantum computing devices. In general, QUBO reformulations of combinatorial problems can be readily obtained by properly penalizing the violation of the problem's constraints in the original problem's objective. However, characterizing tight (i.e., minimal but sufficient) penalty coefficients for this purpose is important and non-trivial for enabling the solution of the resulting QUBO in current and near-term quantum computing devices. Along these lines, we present closed-form characterizations of tight penalty coefficients for two distinct QUBO reformulations of the max k-cut problem whose values depend on the (weighted) degree of the vertices of the graph defining the problem. These findings contribute to the ongoing effort to make quantum computing a viable tool for solving combinatorial problems at scale. We support our theoretical results with illustrative examples and simple numerical results.
Graph partitioning is a fundamental problem in various fields, including computer graphics, high-performance computing, and network design. Traditional graph partitioning algorithms often suffer from high computational complexity, particularly when dealing with large and complex graphs. This research investigates the potential of quantum-inspired optimization techniques, specifically leveraging concepts from quantum annealing, to accelerate the graph partitioning process. We formulate the graph partitioning problem as a Quadratic Unconstrained Binary Optimization (QUBO) problem, allowing us to simulate the behavior of a quantum annealer on classical hardware. The core of our approach involves mapping the graph's connectivity structure onto a QUBO, representing nodes as binary variables and edges as constraints. By exploiting the inherent parallelism of quantum annealing, we aim to find optimal or near-optimal partitions significantly faster than conventional methods. The results demonstrate the feasibility and potential advantages of this quantum-inspired strategy for graph partitioning, offering a promising direction for tackling computationally intensive graph problems.
Recent advances in quantum computing and the increasing availability of quantum hardware have substantially enhanced the practical relevance of quantum approaches to discrete optimization. Among these, the Quadratic Unconstrained Binary Optimization (QUBO) formulation provides a unifying modeling framework for a broad class of NP-hard problems and is naturally suited to quantum computing and quantum-inspired algorithms. Location science, network design, and logistics represent core application domains of discrete optimization, combining high practical impact with substantial computational challenges. In this work, we develop QUBO formulations for several fundamental problems in these domains, including a nonlinear integer formulation of the Discrete Ordered Median Problem (DOMP). Beyond their modeling relevance, these QUBO formulations serve as representative benchmark problems for assessing quantum algorithms and quantum hardware. We further derive a tight bound for the penalty parameter ensuring equivalence between the QUBO formulation and its underlying integer program. Finally, we conduct a comprehensive computational study using QAOA, WS-QAOA, and classical heuristics for QUBO instances of the p-Median Problem and the Fixed-Charge Facility Location Problem (FCFLP), and introduce two effective warm-start strategies for WS-QAOA based on its linear programming relaxation.
The recent availability of the first commercial quantum computers has provided a promising tool to tackle NP hard problems which can only be solved heuristically with present techniques. However, it is unclear if the current state of quantum computing already provides a quantum advantage over the current state of the art in classical computing. This article assesses the performance of the D-Wave 2X quantum annealer on two NP hard graph problems, in particular clique finding and graph partitioning. For this, we provide formulations as Qubo and Ising Hamiltonians suitable for the quantum annealer and compare a variety of quantum solvers (Sapi, QBSolv, QSage provided by D-Wave Sys, Inc.) to current classical algorithms (METIS, Simulated Annealing, third-party clique finding and graph splitting heuristics) on certain test sets of graphs. We demonstrate that for small graph instances, classical methods still outperform the quantum annealer in terms of computing time, even though the quality of the best solutions obtained is comparable. Nevertheless, due to the limited problem size which can be embedded on the D-Wave 2X chip, the aforementioned finding applies to most of problems of general nature solvable on the quantum annealer. For instances specifically designed to fit the D-Wave 2X architecture, we observe substantial speed-ups in computing time over classical approaches.