The Quantum Annealer built by D-Wave, known as Advantage, is currently the largest quantum computer in the world, featuring a topology called “Pegasus.” This groundbreaking system opens new possibilities for solving highly complex problems. The advancement of quantum annealers has spurred experimental demonstrations and intensified research interest, particularly in quantum machine learning. However, the application of quantum annealing in machine learning remains limited due to the lack of conclusive performance evaluations on real-world datasets. There is still no clear consensus on the efficacy of these models in practical scenarios. This work focuses on experimentally evaluating quantum annealing machine learning (QAML) classification methods, specifically Quantum Support Vector Machines (QSVM) and QBoost, on ADMET datasets—one of the most important datasets in the drug discovery domain. We compare QAML with classical machine learning to evaluate their relative performance. This study seeks to address this gap by rigorously comparing the performance of QBoost and QSVM models using ADMET datasets, employing D-Wave’s Quantum Annealer. This work provides a comprehensive analysis of the potential and limitations of quantum annealers in quantum machine learning, with a focus on their application to real-world data in the ADMET domain. The findings offer critical insights into the nuanced advantages and challenges of quantum annealers in advancing machine learning methodologies.
The Quantum Annealer built by D-Wave, known as Advantage, is currently the largest quantum computer in the world, featuring a topology called “Pegasus.” This groundbreaking system opens new possibilities for solving highly complex problems. The advancement of quantum annealers has spurred experimental demonstrations and intensified research interest, particularly in quantum machine learning. However, the application of quantum annealing in machine learning remains limited due to the lack of conclusive performance evaluations on real-world datasets. There is still no clear consensus on the efficacy of these models in practical scenarios. This work focuses on experimentally evaluating quantum annealing machine learning (QAML) classification methods, specifically Quantum Support Vector Machines (QSVM) and QBoost, on ADMET datasets—one of the most important datasets in the drug discovery domain. We compare QAML with classical machine learning to evaluate their relative performance. This study seeks to address this gap by rigorously comparing the performance of QBoost and QSVM models using ADMET datasets, employing D-Wave’s Quantum Annealer. This work provides a comprehensive analysis of the potential and limitations of quantum annealers in quantum machine learning, with a focus on their application to real-world data in the ADMET domain. The findings offer critical insights into the nuanced advantages and challenges of quantum annealers in advancing machine learning methodologies.
Quantum computing (QC) has become a fascinating and popular topic due to its broad range of applications, particularly in machine learning (ML). The intersection of QC and ML is known as Quantum Machine Learning (QML). QML is a field that investigates how QC can enhance ML, making it one of the most exciting areas of research due to the potential of QC in solving complex problems. In this paper, we demonstrate the Quantum Annealing (QA) approach to improving ML in binary classification tasks. We implemented the QBoost algorithm on a few datasets using D-Wave’s quantum computers, specifically the Advantage 1 and Advantage 2 prototypes, incorporating the new feature Fast Anneal.
Quantum computing offers new paradigms in machine learning, notably through Quantum Annealing (QA), which offers promising approaches to optimization problems. This study introduces an application of Multi-tasking Quantum Annealing (MTQA) to enhance multi-class Support Vector Machines (SVMs). Traditional QA methods require multiple cycles to classify multi-class datasets, significantly increasing computational demands. In contrast, MTQA embeds multiple SVM classifiers in parallel on a quantum annealer, thereby reducing the number of required annealing cycles to a single cycle. Utilizing the D-Wave Advantage 6.4 system, we evaluated our method across three benchmark datasets: a synthetic dataset (Blob), subsets of handwritten digits, and the Iris dataset with different feature focuses. Our findings demonstrate that MTQA achieves accuracy equivalent to that of classical Sequential Minimal Optimization (SMO), Simulated Annealing (SA), and standard QA methods while significantly improving computational efficiency. Despite the current limitations in quantum technology and the empirical selection of model parameters, these results highlight the emergent potential of quantum computing in machine learning. Further advancements in quantum algorithm optimization and parameter tuning are anticipated to enhance the efficacy of QA and MTQA, solidifying their practical application roles.
Quantum Machine Learning (QML) has emerged as a promising paradigm for addressing increasing computational and representational demands in materials informatics. While classical models such as Support Vector Machines (SVM) achieve strong predictive performance, they often struggle to capture complex, highly correlated interactions in high-dimensional materials data. QML addresses this challenge by leveraging quantum-mechanical principles to construct expressive feature embeddings, where prospective quantum advantage lies in generating feature spaces that are difficult to approximate classically. In this study, 1,000 crystalline compounds from the Open Quantum Materials Database (OQMD) are evaluated in a binary classification task based on formation-energy stability. The dataset is normalized, reduced to four dimensions via Principal Component Analysis (PCA), and encoded into quantum circuits. Three QML models—QSVM, VQC, and QNN—are benchmarked against a classical SVM using repeated stratified evaluation. Results show that the classical SVM achieves the highest accuracy (91.8% ± 0.012), followed by QSVM (60.8% ± 0.035), while VQC and QNN perform significantly worse. This gap is driven by limited qubit capacity, encoding inefficiencies, restricted circuit expressivity, and optimization challenges. Nevertheless, QSVM demonstrates stable performance, suggesting that potential quantum advantage may emerge from improved feature encoding and kernel design rather than deeper variational circuits.
This thesis explores the integration of quantum computing into Machine Learning (ML), aiming to evaluate the effectiveness and limitations of quantum-enhanced models compared to classical approaches. As quantum technologies continue to develop, they offer the potential for solving complex computational problems more efficiently, particularly in fields requiring high-dimensional data processing. A literature review is conducted to contextualize current advancements in Quantum Machine Learning, highlighting theoretical benefits and existing practical limitations. This work investigates whether quantum methods, specifically the Quantum Support Vector Classifier (QSVC), can provide measurable improvements over its classical counterpart. The QSVC, implemented using IBM’s Qiskit ML library, replaces traditional kernel functions with quantum kernels computed via quantum circuits and feature maps, embedding classical data into a Hilbert space. The experimental portion of this thesis compares classical and quantum models on two distinct datasets: one from the healthcare domain and another from particle physics. Various parameters are tested in a constrained grid search due to the high computational demands of quantum circuits. Results indicate that while quantum models are significantly more resource-intensive, they can achieve comparable or even improved performance on data that has more complex relations between their variables. However, scalability remains a major challenge. This work concludes that although QSVC does not yet consistently outperform classical models, it offers advantages in specific contexts and lays the groundwork for identifying future use cases where quantum computing may offer a practical advantage in ML.
In recent years, the development of quantum annealers has enabled experimental demonstrations and has increased research interest in applications of quantum annealing, such as in quantum machine learning and in particular for the popular quantum Support Vector Machine (SVM). Several versions of the quantum SVM have been proposed, and quantum annealing has been shown to be effective in them. Extensions to multiclass problems have also been made, which consist of an ensemble of multiple binary classifiers. This work proposes a novel quantum SVM formulation for direct multiclass classification based on quantum annealing, called Quantum Multiclass SVM (QMSVM). The multiclass classification problem is formulated as a single quadratic unconstrained binary optimization problem solved with quantum annealing. The main objective of this work is to evaluate the feasibility, accuracy, and time performance of this approach. Experiments have been performed on the D-Wave Advantage quantum annealer for a classification problem on remote sensing data. Results indicate that, despite the memory demands of the quantum annealer, QMSVM can achieve an accuracy that is comparable to standard SVM methods, such as the one-versus-one (OVO), depending on the dataset (compared to OVO: 0.8663 vs 0.8598 on Toulouse, 0.8123 vs 0.8521 on Potsdam). More importantly, it scales much more efficiently with the number of training examples, resulting in nearly constant time (compared to OVO: 85.72s vs 248.02s on Toulouse, 58.89s vs 580.17s on Potsdam). This work shows an approach for bringing together classical and quantum computation, solving practical problems in remote sensing with current hardware.
Machine learning's ability to analyze and predict complex data enables many scientific discoveries and industrial advances. However, state-of-the-art machine learning requires extensive computational resources for training. In machine learning, the training phase is crucial because it enables the model to acquire knowledge from the provided data. The duration of the training process varies significantly, ranging from a few hours to several months. As a result, the computational cost and time constraints hinder researchers from using machine learning. To address this issue, we investigated the possibility of using quantum computers for machine-learning tasks. We compared Date's [1] quantum support vector machine (SVM) approach on a D-Wave Advantage to a classical implementation on AMD Ryzen and Intel Xeon processors. We evaluated both the time-to-solution and the machine-learning performance of the quantum and classical systems. The results of our study demonstrated that SVMs scaledO(N2)on the quantum computer andO(N2d)on the classical computer. Here, N represents the number of samples, and d represents the number of features. So, when trained with a data set with eight million features, we found that the quantum annealer outperformed the classical computer by 3.5-4.5x. The quantum approach maintained a comparable accuracy to the classical approach as well. In conclusion, quantum computers offer a computational advantage over classical computers for machine learning.