6 citations · 15 across the 25 of their papers we have counts for
25 papers
Illustration of Barren Plateaus in Quantum Computing
Gerhard Stenzel, Tobias Rohe, Michael Kölle +3
Variational Quantum Circuits (VQCs) have emerged as a promising paradigm for quantum machine learning in the NISQ era. While parameter sharing in VQCs can reduce the parameter spac…
Evolutionary-Based Circuit Optimization for Distributed Quantum Computing
Leo Sünkel, Jonas Stein, Gerhard Stenzel +3
In this work, we evaluate an evolutionary algorithm (EA) to optimize a given circuit in such a way that it reduces the required communication when executed in the Distributed Quant…
Quality Diversity for Variational Quantum Circuit Optimization
Maximilian Zorn, Jonas Stein, Maximilian Balthasar Mansky +3
Optimizing the architecture of variational quantum circuits (VQCs) is crucial for advancing quantum computing (QC) towards practical applications. Current methods range from static…
Evaluating Parameter-Based Training Performance of Neural Networks and Variational Quantum Circuits
Michael Kölle, Alexander Feist, Jonas Stein +2
In recent years, neural networks (NNs) have driven significant advances in machine learning. However, as tasks grow more complex, NNs often require large numbers of trainable param…
Accelerated VQE: Parameter Recycling for Similar Recurring Problem Instances
Tobias Rohe, Maximilian Balthasar Mansky, Michael Kölle +3
Training the Variational Quantum Eigensolver (VQE) is a task that requires substantial compute. We propose the use of concepts from transfer learning to considerably reduce the tra…
Coconut Palm Tree Counting on Drone Images with Deep Object Detection and Synthetic Training Data
Tobias Rohe, Barbara Böhm, Michael Kölle +3
Drones have revolutionized various domains, including agriculture. Recent advances in deep learning have propelled among other things object detection in computer vision. This stud…
Solving Max-3SAT Using QUBO Approximation
Sebastian Zielinski, Jonas Nüßlein, Michael Kölle +3
As contemporary quantum computers do not possess error correction, any calculation performed by these devices can be considered an involuntary approximation. To solve a problem on…
Sequential Hamiltonian Assembly: Enhancing the training of combinatorial optimization problems on quantum computers
Navid Roshani, Jonas Stein, Maximilian Zorn +3
A central challenge in quantum machine learning is the design and training of parameterized quantum circuits (PQCs). Much like in deep learning, vanishing gradients pose significan…
Optimizing Variational Quantum Circuits Using Metaheuristic Strategies in Reinforcement Learning
Michael Kölle, Daniel Seidl, Maximilian Zorn +3
Quantum Reinforcement Learning (QRL) offers potential advantages over classical Reinforcement Learning, such as compact state space representation and faster convergence in certain…
Architectural Influence on Variational Quantum Circuits in Multi-Agent Reinforcement Learning: Evolutionary Strategies for Optimization
Michael Kölle, Karola Schneider, Sabrina Egger +5
In recent years, Multi-Agent Reinforcement Learning (MARL) has found application in numerous areas of science and industry, such as autonomous driving, telecommunications, and glob…
From Problem to Solution: A general Pipeline to Solve Optimisation Problems on Quantum Hardware
Tobias Rohe, Simon Grätz, Michael Kölle +3
With constant improvements of quantum hardware and quantum algorithms, quantum advantage comes within reach. Parallel to the development of the computer at the end of the twentieth…
MEDIATE: Mutually Endorsed Distributed Incentive Acknowledgment Token Exchange
Philipp Altmann, Katharina Winter, Michael Kölle +3
Recent advances in multi-agent systems (MAS) have shown that incorporating peer incentivization (PI) mechanisms vastly improves cooperation. Especially in social dilemmas, communic…
Aquarium: A Comprehensive Framework for Exploring Predator-Prey Dynamics through Multi-Agent Reinforcement Learning Algorithms
Michael Kölle, Yannick Erpelding, Fabian Ritz +3
Recent advances in Multi-Agent Reinforcement Learning have prompted the modeling of intricate interactions between agents in simulated environments. In particular, the predator-pre…
A Reinforcement Learning Environment for Directed Quantum Circuit Synthesis
Michael Kölle, Tom Schubert, Philipp Altmann +3
With recent advancements in quantum computing technology, optimizing quantum circuits and ensuring reliable quantum state preparation have become increasingly vital. Traditional me…
Quantum Denoising Diffusion Models
Michael Kölle, Gerhard Stenzel, Jonas Stein +3
In recent years, machine learning models like DALL-E, Craiyon, and Stable Diffusion have gained significant attention for their ability to generate high-resolution images from conc…
Quantum Advantage Actor-Critic for Reinforcement Learning
Michael Kölle, Mohamad Hagog, Fabian Ritz +4
Quantum computing offers efficient encapsulation of high-dimensional states. In this work, we propose a novel quantum reinforcement learning approach that combines the Advantage Ac…
ClusterComm: Discrete Communication in Decentralized MARL using Internal Representation Clustering
Robert Müller, Hasan Turalic, Thomy Phan +3
In the realm of Multi-Agent Reinforcement Learning (MARL), prevailing approaches exhibit shortcomings in aligning with human learning, robustness, and scalability. Addressing this,…
Improving Parameter Training for VQEs by Sequential Hamiltonian Assembly
Jonas Stein, Navid Roshani, Maximilian Zorn +3
A central challenge in quantum machine learning is the design and training of parameterized quantum circuits (PQCs). Similar to deep learning, vanishing gradients pose immense prob…
Challenges for Reinforcement Learning in Quantum Circuit Design
Philipp Altmann, Jonas Stein, Michael Kölle +5
Quantum computing (QC) in the current NISQ era is still limited in size and precision. Hybrid applications mitigating those shortcomings are prevalent to gain early insight and adv…
Disentangling Quantum and Classical Contributions in Hybrid Quantum Machine Learning Architectures
Michael Kölle, Jonas Maurer, Philipp Altmann +3
Quantum computing offers the potential for superior computational capabilities, particularly for data-intensive tasks. However, the current state of quantum hardware puts heavy res…
Multi-Agent Quantum Reinforcement Learning using Evolutionary Optimization
Michael Kölle, Felix Topp, Thomy Phan +3
Multi-Agent Reinforcement Learning is becoming increasingly more important in times of autonomous driving and other smart industrial applications. Simultaneously a promising new ap…
Improving Primate Sounds Classification using Binary Presorting for Deep Learning
Michael Kölle, Steffen Illium, Maximilian Zorn +3
In the field of wildlife observation and conservation, approaches involving machine learning on audio recordings are becoming increasingly popular. Unfortunately, available dataset…
Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial Observability
Thomy Phan, Fabian Ritz, Philipp Altmann +5
Stochastic partial observability poses a major challenge for decentralized coordination in multi-agent reinforcement learning but is largely neglected in state-of-the-art research…
VoronoiPatches: Evaluating A New Data Augmentation Method
Steffen Illium, Gretchen Griffin, Michael Kölle +3
Overfitting is a problem in Convolutional Neural Networks (CNN) that causes poor generalization of models on unseen data. To remediate this problem, many new and diverse data augme…