Abstracts-QAI-EN

a:3:{s:6:"locale";s:5:"en_US";s:3:"rtl";i:0;s:9:"flag_code";s:2:"us";}
Quantum Architecture Search for Solving Quantum Machine Learning Tasks

Quantum Architecture Search for Solving Quantum Machine Learning Tasks

Abstract:

Quantum computing is a computing paradigm based on the principles of quantum mechanics. This makes it fundamentally different from classical computing. For selected problem domains, quantum computers are expected to offer a performance advantage, the so-called quantum advantage, which manifests itself in exponentially faster computation times or lower resource requirements. In the current Noisy Intermediate Scale Quantum era, quantum hardware is still limited in performance and highly error-prone. Variational Quantum Circuits represent an approach that is comparatively robust to these limitations. The performance of these quantum circuits is highly dependent on the underlying architecture of the parameterized quantum circuit. The development of powerful, hardware-compatible circuit architectures is therefore an important task, also known as Quantum Architecture Search. Developing good architectures manually is an inefficient and error-prone process. First attempts have been made to automate this process. In addition to Evolutionary Algorithms, Differentiable Architecture Search, and Monte Carlo Tree Search, Reinforcement Learning is another potentially suitable approach for finding good architectures, but it has been relatively little studied. In particular, little is known about its suitability as a search strategy for Machine Learning problems. The goal of this work is to investigate Reinforcement Learning as a suitable search strategy for quantum circuits in the context of Machine Learning problems. For this purpose, the RL-QAS framework is presented, which enables the automated search for circuit architectures using a Reinforcement Learning Agent. The RL-QAS framework is evaluated on the Iris and binary MNIST classification problems. RL-QAS enabled the discovery of architectures that achieve high test accuracy in the classification of the aforementioned datasets while exhibiting low complexity. RL-QAS demonstrated that Reinforcement Learning is indeed suitable for architecture discovery. However, in order for RL QAS to be applied to more complex problems, further development of the approach is necessary.

Author:

Simon Salfer

Advisors:

Michael Kölle, Philipp Altmann, Claudia Linnhoff-Popien

Student Thesis | Published June 2025 | Copyright © QAR-Lab
Direct Inquiries to this work to the Advisors


An Empirical Evaluation of Quantum Annealing-Based Image Classification Using Discriminative Quantum Boltzmann Machines

An Empirical Evaluation of Quantum Annealing-Based Image Classification Using Discriminative Quantum Boltzmann Machines

Abstract:

The Boltzmann machine has been highly influential in the development of artificial intelligence, serving as a foundational framework for energy-based models and neural network research. However, its direct applications in modern deep learning have been severely limited due to computational constraints. Classical sampling methods have consistently proven to be inefficient, rendering the processing of high-dimensional inputs practically infeasible. Therefore, alternatives like the Restricted Boltzmann Machine (RBM) have been introduced, sacrificing expressiveness for faster computations. In contrast, Quantum Boltzmann Machines can efficiently sample from approximate Boltzmann distributions when implemented using quantum algorithms such as quantum annealing. Empirical results suggest that this approach can yield a more efficient sampling process than classical methods, enabling more effective exploration of energy landscapes while reducing computational overhead. Additionally, this also makes full connectivity possible, preserving the expressiveness of the original BM. Nonetheless, to the best knowledge of the author, only a sparse amount of other studies have explored the capability of QBMs for supervised learning. This is particularly true for an application-driven context using real quantum hardware. Thus, the primary goal of this work is the evaluation of the practical effectiveness of QBMs utilizing discriminative learning for the classification of real-world image data using a novel embedding approach to save expensive Quantum Processing Unit time. This is done by employing discriminative QBMs, which always clamp the input units to a data point regardless of the current phase. The model can therefore learn the conditional distribution of a label given a data point. The results demonstrate competitive performance compared to discriminative BMs trained with simulated annealing and discriminative RBMs, while also indicating a slight reduction in the number of training epochs required. Additionally, the embedding approach proposed in this work significantly accelerated sampling, with an average speedup of 69.65% over the conventional embedding.

Author:

Mark Vorapong Seebode

Advisors:

Jonas Stein, Daniëlle Schuman, Claudia Linnhoff-Popien

Student Thesis | Published June 2025 | Copyright © QAR-Lab
Direct Inquiries to this work to the Advisors


Quantum Transformers: Leveraging Variational Quantum Circuits for Natural Language Processing

Quantum Transformers: Leveraging Variational Quantum Circuits for Natural Language Processing

Abstract:

Recent advances in large language models (LLMs) have established transformer architectures as the dominant paradigm in natural language processing (NLP). While these models achieve state of the art performance, their exponential growth in parameter count and computational demands raises concerns regarding scalability, energy consumption and environmental impact. Simultaneously, quantum machine learning (QML) has emerged as a promising field that explores whether quantum computation can offer more efficient learning mechanisms, particularly using variational quantum circuits (VQCs), which have shown competitive performance with fewer parameters. This thesis investigates whether a quantum transformer model can be designed to structurally mirror the classical transformer while remaining feasible for execution on Noisy Intermediate-Scale Quantum (NISQ) hardware. To this end, we propose a modular, NISQ-compatible quantum transformer architecture that reproduces key classical components embedding, multi-head attention and encoder-decoder structure, using VQCs. Each component is implemented using shallow, strongly entangling circuits designed to minimize circuit depth and parameter count. The model is evaluated on synthetic language modeling tasks, comparing quantum and classical variants under matched conditions, including identical token vocabularies and equivalent parameter budgets. Results show that the quantum model is capable of learning simple formal languages, converging rapidly with fewer parameters and in some configurations achieving perfect reconstruction of deterministic token sequences. However, its performance degrades on more complex tasks requiring generalization, where classical models remain superior. These findings demonstrate the feasibility of the proposed quantum transformer architecture on near-term hardware and situate the model as a proof of concept for the architectural potential of encoder-decoder quantum transformers models in NLP.

Author:

Julian Hager

Advisors:

Michael Kölle, Gerhard Stenzel, Thomas Gabor, Claudia Linnhoff-Popien

Student Thesis | Published June 2025 | Copyright © QAR-Lab
Direct Inquiries to this work to the Advisors


Emergent Cooperation in Quantum Multi-Agent Reinforcement Learning Using Communication

Emergent Cooperation in Quantum Multi-Agent Reinforcement Learning Using Communication

Abstract:

Emergent cooperation in classical Multi-Agent Reinforcement Learning has gained significant attention, particularly in the context of Sequential Social Dilemmas. While classical reinforcement learning approaches have demonstrated to be capable of emergent cooperation, research on extending these methods to the emerging field of Quantum Multi-Agent Reinforcement Learning remains limited, particularly through the usage of communication. In this work, we apply the two-phase communication protocol Mutual Acknowledgment Token Exchange (MATE), its extension Mutually Endorsed Distributed Incentive Acknowledgment Token Exchange (MEDIATE), the peer rewarding mechanism Gifting and Reinforced Inter-Agent Learning (RIAL), an approach to learn a discrete communication protocol, to quantum Q-Learning. We evaluate the resulting eight approaches in terms of their impact on emergent cooperation in three Sequential Social Dilemmas, namely the Iterated Prisoner’s Dilemma, the Iterated Stag Hunt and the Iterated Game of Chicken. Our experimental results show that the approaches MATETD, AutoMATE, MEDIATE-I and MEDIATE-S achieved high levels of cooperation across all three Sequential Social Dilemmas, demonstrating that communication is a viable method to achieve emergent cooperation in Quantum Multi-Agent Reinforcement Learning.

Author:

Christian Reff

Advisors:

Michael Kölle, Leo Sünkel, Claudia Linnhoff-Popien

Student Thesis | Published May 2025 | Copyright © QAR-Lab
Direct Inquiries to this work to the Advisors


Determining links in product data using Quantum Restricted Boltzmann Machines

Determining links in product data using Quantum Restricted Boltzmann Machines

Abstract:

The increasing share of software in products not only drives innovation but also increases complexity. To minimize the risk of malfunctions in software-intensive products and ensure traceability, links between development stages and production data are necessary. These are mandated by regulations such as ISO/IEC 15288 and DIN/ISO 26262. The Digital Data Package standard enables the management of such links. However, implicit links currently have to be created manually, which leads to challenges due to the scope and frequent product changes. A promising approach for the automatic identification of links is the use of classifiers. In particular, Quantum Restricted Boltzmann Machines offer a viable solution due to the limited availability of linked development data and their high susceptibility to noise. For evaluation, classical neural networks and pre-trained classifiers are used. As established methods in pattern recognition, they serve as a baseline for assessing new classifiers.

Author:

Simon Hehnen

Advisors:

Michael Kölle, Jonas Stein, Dr. Fabrice Mogo Nem (PROSTEP AG), Claudia Linnhoff-Popien

Student Thesis | Published April 2025 | Copyright © QAR-Lab
Direct Inquiries to this work to the Advisors


Emerging Cooperation through Quantum Entanglement in Multi-Agent Systems

Emerging Cooperation through Quantum Entanglement in Multi-Agent Systems

Abstract:

This thesis investigates the feasibility of quantum entanglement enhancing cooperation in multi-agent reinforcement learning. Utilizing the iterated prisoner dilemma as a benchmark, we propose a decentralized multi-agent reinforcement learning framework where two MARL agents equipped with variational quantum circuits can affect each other through quantum entanglement. Unlike existing approaches that rely on dedicated quantum communication channels, this thesis examines whether entanglement alone can facilitate cooperative equilibria. Therefore, we evaluate the effects of different entanglement architectures to develop mutual cooperative strategies that escape the Nash equilibrium. The results of our experiments indicate that while entanglement can facilitate strategies that outperform the defection baseline, long-term cooperative behavior remains unfeasible, suggesting that quantum correlations alone are insufficient to sustain cooperative strategies in multi-agent reinforcement learning settings.

Author:

Marvin Heinrich

Advisors:

Michael Kölle, Leo Sünkel, Claudia Linnhoff-Popien

Student Thesis | Published March 2025 | Copyright © QAR-Lab
Direct Inquiries to this work to the Advisors


Distributed Quantum Machine Learning -Training and Evaluating a Machine Learning Model on a Distributed Quantum Computing Simulator

Distributed Quantum Machine Learning -Training and Evaluating a Machine Learning Model on a Distributed Quantum Computing Simulator

Abstract:

The training and execution of machine learning models on quantum hardware is typically limited by the number of available qubits. A potential approach to overcoming this limitation is Distributed Quantum Machine Learning (DQML), where models are partitioned and executed across multiple quantum computers. While this increases the number of available qubits and potentially enables the training of larger models, it also introduces substantial classical and quantum communication overhead, leading to increased computational costs and extended training times. To investigate this approach and its limitations, this thesis presents a DQML model using a classical server and two quantum clients, implemented with the distributed quantum framework NetQASM. We evaluated the model on datasets with two and four features using a quantum network simulator and it achieved classification performance comparable to that of a centralized quantum baseline. To address the communication overhead, which resulted in training times of 50 to 500 minutes per epoch, optimizations in circuit design, entanglement generation, and distributed gate execution were implemented and evaluated. These adaptations led to a reduction in runtime of up to 60% while maintaining competitive classification accuracy.

Author:

Kian Izadi

Advisors:

Leo Sünkel, Michael Kölle, Thomas Gabor, Claudia Linnhoff-Popien

Student Thesis | Published March 2025 | Copyright © QAR-Lab
Direct Inquiries to this work to the Advisors


QUBO-Generation for (MAX-)3SAT via generative AI-Methods

QUBO-Generation for (MAX-)3SAT via generative AI-Methods

Abstract:

Creating QUBOs for 3-SAT formulas using pattern QUBOs poses several challenges. Generating pattern QUBOs and building the QUBO structure itself is technically demanding due to the brute-force approach. In this study, two machine-learning approaches for QUBO generation given a 3-SAT formula are tested. Various encoding methods were explored for representing formulas and matrices. Formula encodings included vector, Word2Vec, and BERT-based methods, while latent representations were tested on QUBOs. As an initial model, a conditional autoencoder was used, with variations like dual encoders and pretrained encoders based on a RESNET18 architecture also evaluated. Accurate QUBOs could be generated for formulas with a single clause, but for formulas with up to four clauses, energy levels of solution and non-solution states overlapped. Finally, a conditional diffusion model was implemented and trained on 5 and 7 clause random formulas using vector, Word2Vec, and BERT formula embeddings. QUBOs generated with BERT formula embeddings fulfilled the highest average number of clauses per formula, though most formulas remained unsolved. Training with masked diffusion further improved performance, as QUBOs generated with masking fulfilled, on average, one additional clause. However, this approach requires a predefined mask during data generation. The sparse QUBO data structure and challenges in encoding 3-SAT formulas are likely primary factors behind these results.

Author:

Philippe Wehr

Advisors:

Sebastian Zielinski, Michael Kölle, Claudia Linnhoff-Popien

Student Thesis | Published March 2025 | Copyright © QAR-Lab
Direct Inquiries to this work to the Advisors


Evaluating Parameter-Based Training Performance of Neural Networks and Variational Quantum Circuits

Evaluating Parameter-Based Training Performance of Neural Networks and Variational Quantum Circuits

Abstract:

In recent years, neural networks (NN) have played a central role in significant advancements in the field of machine learning. The increasing complexity of machine learning tasks leads to NNs with a growing number of trainable parameters, resulting in high computational and energy demands. Variational quantum circuits (VQC) are a promising alternative. They leverage quantum mechanics to model complex relationships and tend to require fewer trainable parameters compared to NNs. In this work, we evaluate and compare the training performance of NNs and VQCs on simple supervised learning and reinforcement learning tasks, considering multiple models with varying numbers of parameters. The experiments with VQCs are conducted using a simulator. To approximate how long training the VQCs would take using currently available real quantum hardware, selected parts of the training process are executed using a real quantum computer. Our results confirm that VQCs can achieve performance comparable to NNs while requiring significantly fewer parameters. Despite longer training times, our findings suggest that VQCs could be advantageous for certain machine learning tasks, particularly as quantum technology continues to rapidly advance, algorithms are optimized, and VQC architectures are improved.

Author:

Alexander Feist

Advisors:

Michael Kölle, Jonas Stein, Claudia Linnhoff-Popien

Student Thesis | Published January 2025 | Copyright © QAR-Lab
Direct Inquiries to this work to the Advisors


Reinforcement learning-supported state preparation using parameterized quantum gates

Reinforcement learning-supported state preparation using parameterized quantum gates

Abstract:

This thesis investigates the application of reinforcement learning (RL) in order to optimize the state preparation in parameterized quantum circuits. By using RL algorithms, an agent is trained to find the optimal sequence of quantum gates so as to reconstruct predetermined target states. Particular attention is paid to the challenges of using parametric gates, which require continuous optimization when compared to discrete circuits. Dierent approaches, including one- and two-stage methods as well as hyperparameter optimizations, are evaluated experimentally. The results show that RL-based methods can successfully contribute to the reduction of circuit depth, however this applies mainly to simple circuits. More complex circuits require deeper adaptations of the optimization strategy in order to achieve similar success.

Author:

Isabella Debelic

Advisors:

Michael Kölle, Philipp Altmann, Claudia Linnhoff-Popien

Student Thesis | Published December 2024 | Copyright © QAR-Lab
Direct Inquiries to this work to the Advisors


Page 1 of 3