Genetic algorithms (GAs) have recently emerged as a competitive alternative to gradient-based optimization for training variational quantum classifiers (VQCs). However, existing GA-based training frameworks suffer from severe computational bottlenecks as a result of the repeated executions of large populations of quantum circuits across multiple data samples. In this work, we introduce a JAX-based genetic training framework for VQCs that takes advantage of population-level and data-level vectorization to drastically reduce execution time on classical simulation backends. Through an extensive experimental evaluation involving VQCs up to 15 qubits, multiple dataset sizes, and varying population sizes, we demonstrate speedups up to four orders of magnitude with respect to the state-of-the-art GA-based training of VQCs. Acceleration gains are particularly pronounced on GPUs. Importantly, these computational gains do not come at the expense of model performance, as comparable classification accuracy is achieved across all experiments performed.
Genetic algorithms (GAs) have recently emerged as a competitive alternative to gradient-based optimization for training variational quantum classifiers (VQCs). However, existing GA-based training frameworks suffer from severe computational bottlenecks as a result of the repeated executions of large populations of quantum circuits across multiple data samples. In this work, we introduce a JAX-based genetic training framework for VQCs that takes advantage of population-level and data-level vectorization to drastically reduce execution time on classical simulation backends. Through an extensive experimental evaluation involving VQCs up to 15 qubits, multiple dataset sizes, and varying population sizes, we demonstrate speedups up to four orders of magnitude with respect to the state-of-the-art GA-based training of VQCs. Acceleration gains are particularly pronounced on GPUs. Importantly, these computational gains do not come at the expense of model performance, as comparable classification accuracy is achieved across all experiments performed.
Variational Quantum Circuits (VQCs) are viable alternatives for implementing quantum circuits in current quantum processors. VQCs are reduced circuits with parameters that are trained to minimize a loss function for a given problem. In this work, we propose an approach to optimize the parameters of a VQC using Genetic Algorithms (GAs). We explored different GA configurations, on 3 databases - Sonar, Cancer and Banknotes datasets, comparing the proposed approach with 2 classical optimizers based on gradient descent. The results show that genetic algorithms can effectively optimize the weights of variational circuits to achieve high classification accuracy with convergence speed up to 7.3 times (in Sonar Database), 4.8 times (Cancer Database), and 3.7 times (Banknote Database) compared with the traditional optimizers. The experimental results indicate that the genetic algorithm achieves performance metrics that are significantly superior or at least comparable to those obtained by gradient descent-based optimizers, demonstrating the potential and robustness of evolutionary strategies in training variational quantum circuits.
Recently, Variational Quantum Circuits (VQCs) are attracting considerable attention among quantum algorithms thanks to their robustness to the noise characterizing the current quantum devices. In detail, VQCs involve parameterized quan-tum circuits to be trained by means of a classical optimizer that makes queries to the quantum device. VQCs play a key role in several applications including quantum classifiers where the Hilbert space is used as feature space. Currently, the most used classical optimizer to learn V QCs is the gradient descent method. However, the so-called barren plateaus issue causes gradients of cost functions to become exceedingly small as the dimension of the classification problem is increased. As consequence, gradient descent method could be not efficient in real-world classification problems. This paper proposes to apply Genetic Algorithms (GAs) to train VQCs used as quantum classifiers. As shown in the experiments, the application of GAs results in accurate solutions obtained with a reduced number of queries to quantum devices.
Hybrid Quantum Neural Networks (HQNNs) combine classical learning with parameterized quantum circuits, but their practical performance is often limited by (i) the noise of Noisy Intermediate-Scale Quantum (NISQ) devices and (ii) the large, discrete design space of quantum circuit architectures. Moreover, HQNNs are commonly trained using a fixed circuit and a single backend, even though deployment frequently targets heterogeneous backends where compilation and execution characteristics may differ. To address these challenges, we propose GAT-QNN, a genetic algorithm (GA)-based framework that trains a macroCircuit (search space) by iteratively sampling microCircuits (subcircuits), training them, and reintegrating their learned parameters into the macroCircuit. After training, we run an independent GA-driven inference stage that evaluates candidate microCircuits using the trained macroCircuit weights and selects top-performing architectures for deployment. This two-stage approach enables backend-aware microCircuit selection without retraining each candidate architecture and can also reduce computational resources (gate count) by deploying smaller microCircuits derived from the macroCircuit. We validate the approach on MNIST classification (four classes) and report consistent 22-23% test accuracy gains for GA-driven inference across multiple backends.
Quantum computing holds promise across various fields, particularly with the advent of Noisy Intermediate-Scale Quantum (NISQ) devices, which can outperform classical supercomputers in specific tasks. However, challenges such as noise and limited qubit capabilities hinder its practical applications. Variational Quantum Algorithms (VQAs) offer a viable strategy to achieve quantum advantage by combining quantum and classical computing. Leveraging on VQAs, the performance of Variational Quantum Classifiers (VQCs) is competitive with many classical classifiers. This work implements a VQC using a silicon-based quantum photonic microprocessor and a classical computer, demonstrating its effectiveness in nonlinear binary and multi-classification tasks. An efficient gradient free genetic algorithm is employed for training. The VQC's performance was evaluated on three synthetic binary classification tasks with square-, circular-, and sine-shape decision boundaries and a real-world multiclass Iris dataset. The accuracies on the three binary classification tasks were 87.5%, 92.5%, and 85.0%, respectively, and 98.8% on the real world Iris dataset, highlighting the platform's potential to handle complex data patterns.
In the field of quantum computing, Variational Quantum Algorithms (VQAs) combine quantum circuits with classical optimization to perform several tasks including classification and regression. Although gradient-based methods are commonly used for their training, these methods suffer from barren plateaus, noise sensitivity, and high computational costs. In this scenario, Evolutionary Algorithms (EAs) provide a gradient-free alternative for training VQAs enabling the discovery of high-quality solutions while requiring limited hardware resources. Unfortunately, the number of software tools aimed to the application of EAs for training of VQAs is limited and, moreover, they rarely exploits GPU acceleration. In order to bridge this gap, this work presents f-EVOVAQ, a Python package that extends the EVOVAQ framework by implementing vectorized evolutionary operators on GPU using CuPy arrays. The package enables efficient population-level optimization while remaining user-friendly for non-experts in evolutionary computation. Experiments on quantum classification tasks demonstrate significant reductions in optimization time and improved scalability, with limitations arising from GPU–CPU data transfers.
Quantum Machine Learning (QML) is a newly emerging research area at the intersection of classical machine learning (CML) and quantum computing (QC). Data is becoming voluminous rapidly, so it is challenging for classical computers to train Machine Learning (ML) models over massive datasets. The hope is that quantum physics' intrinsic features, such as entanglement, superposition, and interference, could be exploited as resources for training ML models on big datasets that would otherwise be relatively impossible for classical computers. It is theoretically proven that quantum computers have an exponential-time advantage over their classical counterparts in solving several problems, e.g., complex large dimensional matrix multiplication, factorization problem, unstructured database search, etc. QML models attempt to find a quantum advantage over their classical counterparts. Variational Quantum Classifiers (VQC) are hybrid quantum neural networks to perform the task of classification using QML models. VQC models in the present NISQ (Noisy Intermediate Scale Quantum — 50 to 100 qubits) era can produce comparable and even better results than Classical models. In this article, we examined the performance of a VQC while performing a simple binary classification task. In this article, we use a VQC to evaluate this method's performance empirically. We constructed a VQC to predict the label of fresh input for the typical Iris dataset comprising pairings of target outputs and training inputs. Our quantum classifier can reasonably predict species labels using only four qubits. These levels are fairly good compared to the accuracy levels attained by classical classifiers.