The rapid development of Machine Learning (ML) algorithms across domains necessitates efficient Hyperparameter Optimization (HPO) to tailor models to specific tasks. Classical HPO techniques become prohibitively slow as model size and search space dimensionality grow. Quantum computing, particularly the Quantum Approximate Optimization Algorithm (QAOA), offers a principled way to explore large combinatorial spaces, but existing QAOA approaches are limited in black-box ML settings, where objective evaluations are expensive. The need for fast yet accurate HPO is most acute in security-critical applications such as Unmanned Aerial Vehicle (UAV) fingerprinting, where defenders must identify hostile drones within seconds. To address this challenge, we propose a QAOA-Based High-Speed Weighted Black-box Hyperparameter Optimization (QWBO), a generic HPO method that directly encodes discretized hyperparameters into qubits. A customized QAOA circuit imposes data-driven penalty weights, and its low-energy states decode to the optimal hyperparameter set. We evaluate QWBO on a realworld XGBoost-based UAV fingerprinting task. QWBO attains 93% classification accuracy, surpassing grid search and Bayesian optimization while requiring far less runtime. Moreover, its runtime grows sublinearly with search space size, demonstrating strong potential for rapid, large-scale HPO across diverse ML models and security domains.
The rapid development of Machine Learning (ML) algorithms across domains necessitates efficient Hyperparameter Optimization (HPO) to tailor models to specific tasks. Classical HPO techniques become prohibitively slow as model size and search space dimensionality grow. Quantum computing, particularly the Quantum Approximate Optimization Algorithm (QAOA), offers a principled way to explore large combinatorial spaces, but existing QAOA approaches are limited in black-box ML settings, where objective evaluations are expensive. The need for fast yet accurate HPO is most acute in security-critical applications such as Unmanned Aerial Vehicle (UAV) fingerprinting, where defenders must identify hostile drones within seconds. To address this challenge, we propose a QAOA-Based High-Speed Weighted Black-box Hyperparameter Optimization (QWBO), a generic HPO method that directly encodes discretized hyperparameters into qubits. A customized QAOA circuit imposes data-driven penalty weights, and its low-energy states decode to the optimal hyperparameter set. We evaluate QWBO on a realworld XGBoost-based UAV fingerprinting task. QWBO attains 93% classification accuracy, surpassing grid search and Bayesian optimization while requiring far less runtime. Moreover, its runtime grows sublinearly with search space size, demonstrating strong potential for rapid, large-scale HPO across diverse ML models and security domains.
The utilization of unmanned aerial vehicles (UAVs) in defense for functions, such as delivery and surveillance, has surged due to the fast progress of technology. UAV tracking and navigation system optimization is critical as UAV operations become more complicated. Quantum computing (QC) can significantly improve optimization procedures for real-time tracking, overcoming computational challenges and enhancing efficiency in UAV operations by handling large amounts of data. The study’s objective is to establish how QC performs in the optimization of UAV tracking. A novel Dynamic Kookaburra-tuned Malleable Convolutional Neural Network (DK-MCNN) is proposed to improve the tracking performance of UAVs. The data collected from video feeds from cameras mounted on UAVs, readings from GPS and other sensors outlining the specific paths and maneuvers the UAV will perform, ensuring diverse scenarios, including various terrains and environments. The data preprocessed using data cleaning and normalization involve removing erroneous or redundant data to ensure high-quality datasets. The study specifically focuses on leveraging QC into UAV tracking systems and promises to enhance performance, including speed, optimization, data handling and robustness. This technology has the potential to transform UAV operations, making them more efficient, reliable and capable of handling complex tasks in dynamic environments. The study evaluates the tracking accuracy, computational efficiency and resilience of the proposed method compared to traditional approaches across a range of operating situations. Extensive simulations of several tracking scenarios, encompassing urban, rural and disaster response situations, are employed to assess the efficacy of UAVs in monitoring and navigating across dynamic terrain. The outcomes illustrate the potential for real-time applications in UAV systems, by showing that the suggested technique dramatically decreases processing time and improves tracking accuracy, when compared to conventional algorithms.
This study extends previous work on quantum-enhanced selection operators [Von Dollen et al.(2022)], where selection operators of evolutionary algorithms for classical black-box optimization are framed as quadratic binary optimization (QUBO) models, applied to black-box objective functions. We test our algorithms using both elitist and non-elitist strategies. First, we benchmark all heuristics over black-box, multi-modal functions. We find that for 94.4% of test cases, our method shows performance improvements with respect to fitness. Then, we similarly benchmark over the problem of hyperparameter selection for machine learning models, also a black-box optimization problem, and compare it to random search. We find that our method achieves some improvement with an average validation accuracy of 98.492% and highest ranking of 4.529412 (out of 5) when averaged across all test cases. We also apply our method towards neuroevolution, where we evolve weight spaces for small feedforward neural networks for learning tasks. In these settings, our method shows improved average reward in the reinforcement learning case and increased velocity in learning the XOR function.
Hyperparameter optimization (HPO) for neural networks on tabular data is critical to a wide range of applications, yet it remains challenging due to large, non-convex search spaces and the cost of exhaustive tuning. We introduce the Quantum-Inspired Bilevel Optimizer for Neural Networks (QIBONN), a bilevel framework that encodes feature selection, architectural hyperparameters, and regularization in a unified qubit-based representation. By combining deterministic quantum-inspired rotations with stochastic qubit mutations guided by a global attractor, QIBONN balances exploration and exploitation under a fixed evaluation budget. We conduct systematic experiments under single-qubit bit-flip noise (0.1\%--1\%) emulated by an IBM-Q backend. Results on 13 real-world datasets indicate that QIBONN is competitive with established methods, including classical tree-based methods and both classical/quantum-inspired HPO algorithms under the same tuning budget.
The increasing availability of quantum hardware has stimulated interest in applying quantum algorithms to combinatorial optimization problems. Collision avoidance for unmanned aerial vehicles (UAVs) is one such challenge due to the computational complexity of coordinating multiple agents in shared airspace. In this paper, we formulate the problem as a Quadratic Unconstrained Binary Optimization (QUBO) model that captures route selection and collision constraints, enabling the use of the Quantum Approximate Optimization Algorithm (QAOA). To improve efficiency, we introduce a constrained QAOA Ansatz employing an XY-mixer that preserves one-hot route assignment constraints and restricts the search space to valid solutions. We evaluate the approach through noiseless simulations and device-based noise models, analyzing its behavior under realistic conditions and highlighting the opportunities and limitations of near-term quantum hardware for multi-agent routing problems.
Quantum-Enhanced Machine Learning Model Optimization explores the potential of leveraging quantum algorithms to dramatically improve the training process of machine learning models, particularly in parameter optimization and hyperparameter selection. This paper investigates the application of quantum algorithms, specifically quantum approximate optimization algorithms (QAOA), to accelerate the training of complex models. The core claim is that utilizing quantum computing will yield substantial improvements in model performance and efficiency compared to traditional machine learning techniques. The research will detail the process of applying QAOA to a specific model type and will present results demonstrating the potential for enhanced training speed and improved model accuracy. This work offers a novel approach to optimizing machine learning models using quantum principles.
The main object of study of this work is the Quantum Approximate Optimization Algorithm (QAOA) —the best-known heuristic quantum algorithm for addressing combinatorial optimization problems. Despite its popularity, QAOA poses major challenges. Namely, its performance remains poorly understood, especially in the low depth regime most relevant to near-term quantum computing. Besides, the algorithm is of variational nature, relying on several hyperparameters to be classically trained. In this work, we contribute to addressing these issues by developing techniques to understand the performance of QAOA at low depth, and deducing from these pretrained hyperparameters, thereby eliminating or considerably reducing the need for a classical optimization loop. We first consider applying QAOA to constraint satisfaction problems with the goal of maximizing the algorithm’s approximation ratio (fraction of satisfied constraints). As a particular example, we consider QAOA applied to MAXCUT on non-regular graphs, showing how analytic techniques provide good guess hyperparameters in this setting. Next, we analyze the performance of QAOA on a well-studied constraint satisfaction problem: random k-SAT. In this case, the performance is measured by the probability of finding an assignment satisfying all constraints (“success probability”). To estimate this quantity, we develop new techniques, mapping quantum expectation values of the QAOA circuits to classical spin models. We further show how these techniques can be generalized to a larger family of random constraint satisfaction problems. We conclude the work by two feasibility studies inspired by real-world use cases encountered in collaborations with industrial partners: peptide sampling, and solving flow problems. These problems are naturally phrased by encoding combinatorial variables in qudits, a relatively unexplored setting in the existing literature. We present partial analytic and numerical results for optimal QAOA hyperparameters and the scaling of its success probability in this framework, underlining potential specific difficulties when using QAOA with qudits.