Effective feature selection is essential for enhancing the performance of artificial intelligence models. It involves identifying feature combinations that optimize a given metric, but this is a challenging task due to the problem's exponential time complexity. In this study, we present an innovative heuristic called Evolutionary Quantum Feature Selection (EQFS) that employs the Quantum Circuit Evolution (QCE) algorithm. Our approach harnesses the unique capabilities of QCE, which utilizes shallow depth circuits to generate sparse probability distributions. Our computational experiments demonstrate that EQFS can identify good feature combinations with quadratic scaling in the number of features. To evaluate EQFS's performance, we counted the number of times a given classical model assesses the cost function for a specific metric, as a function of the number of generations.
Effective feature selection is essential for enhancing the performance of artificial intelligence models. It involves identifying feature combinations that optimize a given metric, but this is a challenging task due to the problem's exponential time complexity. In this study, we present an innovative heuristic called Evolutionary Quantum Feature Selection (EQFS) that employs the Quantum Circuit Evolution (QCE) algorithm. Our approach harnesses the unique capabilities of QCE, which utilizes shallow depth circuits to generate sparse probability distributions. Our computational experiments demonstrate that EQFS can identify good feature combinations with quadratic scaling in the number of features. To evaluate EQFS's performance, we counted the number of times a given classical model assesses the cost function for a specific metric, as a function of the number of generations.
Quantum computing combined with machine learning, is a promising emerging field for tackling problems that are extremely expensive or fundamentally infeasible for classical computers. Nonetheless, design of the optimal quantum circuit for machine learning is a major challenge, which can be attributed to the exponential search space of the quantum gate arrangement and unmatched structured design methods. To resolve this, our work introduces a novel automated framework for quantum architecture search (AQAS) that adopts both meta-learning and evolutionary algorithms to automatically learn, transfer, and optimize quantum circuit architectures to suit different machine learning tasks. Our strategy relies on meta-learning to introduce a learning scheme, i.e. it allows the AQAS system to generalize across distributions by learning from a shared structural and functional prior from the distribution of machine learning problems. This enables the approach to quickly home in effective quantum circuit implementations for new tasks with low data or retraining. At the same time, we use evolutionary algorithms– mimicking natural selection– to breed populations of quantum circuit architectures. These circuits are represented in genotypes, are varied under mutation and crossover, and are selected according to a fitness function that blends quantum resource utilization (e.g., depth, qubits) with task-specific performance (e.g., classification accuracy or loss). The architecture is realized in a mixed quantum-classical environment, with quantum circuits simulated on quantum simulators and/or Noisy-Intermediate-Scale-Quantum (NISQ) devices. We verify the effectiveness of our approach on a number of benchmarked datasets and tasks which range from quantum-aided image recognition, time series prediction to medical diagnostics. We demonstrate that AQAS can discover compact, high-performing quantum models, which generalize better and are computationally more efficient than the custom-built quantum models.
Binary optimization problems are emerging as potential candidates for useful applications of quantum computing. Among quantum algorithms, the quantum approximate optimization algorithm (QAOA) is currently considered the most promising method to obtain a quantum advantage for such problems. The QAOA method uses a classical counterpart to perform optimization in a hybrid approach. In this paper, we show that the recently introduced method called quantum circuit evolutionary (QCE) also has potential for applications in binary optimization problems. This methodology is classical optimizer-free, but, for some scenarios, may have convergence stagnation as a consequence of smooth circuit modifications at each generation. To avoid this drawback and accelerate the convergence capabilities of QCE, we introduce a framework using an adaptive cost function (ACF), which varies dynamically with the circuit evolution. This procedure accelerates the convergence of the method. Applying this new approach to instances of the set partitioning problem, we show that QCE-ACF achieves convergence performance identical to QAOA but with a shorter execution time. Finally, experiments in the presence of induced noise show that this framework is quite suitable for the noisy intermediate-scale quantum era.
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.
Abstract In machine learning, fewer features reduce model complexity. Carefully assessing the influence of each input feature on the model quality is therefore a crucial preprocessing step. We propose a novel feature selection algorithm based on a quadratic unconstrained binary optimization (QUBO) problem, which allows to select a specified number of features based on their importance and redundancy. In contrast to iterative or greedy methods, our direct approach yields higher-quality solutions. QUBO problems are particularly interesting because they can be solved on quantum hardware. To evaluate our proposed algorithm, we conduct a series of numerical experiments using a classical computer, a quantum gate computer, and a quantum annealer. Our evaluation compares our method to a range of standard methods on various benchmark data sets. We observe competitive performance.
Genetic algorithms are highly effective optimization techniques for many computationally challenging problems, including combinatorial optimization tasks like portfolio optimization. Quantum computing has also shown potential in addressing these complex challenges. Combining these approaches, quantum genetic algorithms leverage the principles of superposition and entanglement to enhance the performance of classical genetic algorithms. In this work, we propose a novel quantum genetic algorithm introducing an innovative crossover strategy to generate quantum circuits from a binary solution. We incorporate a heuristic method to encode entanglement patterns from parent solutions into circuits for the next generation. Our algorithm advances quantum genetic algorithms by utilizing a limited number of entanglements, enabling efficient exploration of optimal solutions without significantly increasing circuit depth, making it suitable for near-term applications. We test this approach on a portfolio optimization problem using an IBM 127 qubits Eagle processor (ibm_quebec) and simulators. Compared to state-of-the-art algorithms, our results show that the proposed method improves fitness values by 33.6% over classical genetic algorithm and 37.2% over quantum-inspired genetic algorithm, using the same iteration counts and population sizes with real quantum hardware employing 100 qubits. These findings highlight the potential of current quantum computers to address real-world utility-scale combinatorial optimization problems.
Quantum computing and evolutionary algorithms are collaborating and combining to create a new era of computational problem-solving. Natural-selection-based evolution algorithms have demonstrated efficacy in optimizing complicated systems by iteratively improving solutions. However, quantum computing offers an entirely novel technique to handle information using superposition and entanglement, potentially accelerating optimization procedures. This study examines the theoretical underpinnings and practical implications of recent developments in quantum-enhanced evolutionary algorithms. A unique case study on 5G networks demonstrates the application of these methods to optimization problems in next-generation communication systems. We also emphasize their influence in fields where quantum-assisted evolutionary techniques spur innovation, such as financial modeling, bioinformatics, machine learning, and cryptography. Despite their revolutionary promise, several obstacles remain, such as the scalability of quantum hardware, noise sensitivity, and converting conventional evolutionary mechanisms to quantum frameworks. Developing hybrid quantum-classical and novel optimization approaches will be crucial in advancing artificial intelligence, data analytics, and decision-making systems. The author combines quantum computing with evolutionary principles to explain an advanced computational framework that has diverse scientific concepts as well as industrial applications.