arXiv subjects

Georg Kruse

Publications and source records attributed to Georg Kruse.

11 recordsLinked to original sources

arXiv2026

The QuaST Decision Tree: Achieving Automation With Data-Based Recommendations

Quantum computers are increasingly powerful. Software tools for the development of quantum-enhanced algorithms are maturing. However, the software stack still lacks the connection to applications that would enable hybrid algorithms combining classical and quantum computing steps. End users need to be assisted in choosing the best combination of preprocessing, postprocessing, classical and quantum algorithms options. The application-facing software stack is therefore required to cover problem modeling, encoding, algorithm selection and hyperparameter tuning. A variety of tools exist for specific recommendations. The QuaST Decision Tree reflects the complexity in combining individual decisions in its modular network structure, consisting of flexible computation nodes with modular recommendations. It can easily be configured to serve in an industrial solver, an HPC software stack, or for rapid prototyping in development. The key ingredient, automation, is delivered by modules. We present one such module judging the feasibility of variational algorithms based on a robust scalability analysis and classification of problem instances. The automation improves the performance of end-to-end solutions, highlights the benefit to be gained from the hybrid quantum solution, reduces expensive trial-and-error testing, and leads to an improved utilization of quantum devices for a practical benefit.

quant-ph↗

arXiv2026

jNO: A JAX Library for Neural Operator and Foundation Model Training

jNO (jax Neural Operators) is a JAX-native library for neural operators and foundation models with unified support for both data-driven and physics-informed training. Its core design is a tracing system in which domains, model calls, residuals, supervised losses, and diagnostics are written in one symbolic language and compiled into one optimization pipeline. This allows users to move between operator regression, mesh-aware residual evaluation, and PDE-constrained training without restructuring the surrounding code. jNO also supports multi-model compositions, fine-grained control at parameter level (model, optimizer, and learning rate), hyperparameter tuning, and JAX-native workflows for translated PDE foundation-model families. The source repository is available at https://github.com/FhG-IISB/jNO.

cs.LG↗

arXiv2026

Physics-informed fine-tuning of foundation models for partial differential equations

Foundation models for partial differential equations (PDEs) have emerged as powerful surrogates pre-trained on diverse physical systems, but adapting them to new downstream tasks remains challenging due to limited task-specific data and distribution shifts. While fine-tuning has proven transformative in natural language processing, best practices for adapting PDE foundation models remain underexplored. Although physics-informed training has successfully trained accurate solvers across a wide range of PDE problems, its potential for fine-tuning data-based foundation models has not been systematically studied. In this work, we introduce a physics-informed fine-tuning framework that adapts pre-trained PDE foundation models by incorporating physical constraints (PDE residuals and boundary conditions) directly into the fine-tuning objective. This enables effective adaptation in data-scarce regimes while promoting physical consistency. We evaluate our method on a downstream task composed of an unseen PDE class and compare it with data-driven finetuning counterparts. Our results demonstrate that physics-informed fine-tuning achieves competitive accuracy without requiring PDE solutions for training. Furthermore, a hybrid fine-tuning strategy yields superior generalization to out-of-distribution scenarios when only minimal training data is available. These findings establish physics-informed fine-tuning as a scalable and data-efficient paradigm, providing a physically interpretable pathway for adapting foundation models in scientific machine learning.

cs.LG↗

arXiv2026

QAOA-Predictor: Forecasting Success Probabilities and Minimal Depths for Efficient Fixed-Parameter Optimization

Quantum Computing promises to solve complex combinatorial optimization problems more efficiently than classical methods, with the Quantum Approximate Optimization Algorithm (QAOA) being a leading candidate. Recent fixed-parameter variations of QAOA eliminate costly run-time optimization, but determining their optimal initialization as well as the number of required layers (p) for a target solution remains a critical, unsolved challenge. In this work, we propose a novel approach using a Graph Neural Network (GNN) to predict QAOA performance: Based on a graph representation of the problem, the GNN forecasts the probability of the optimal solution in the resulting distribution across different parameter initializations and layer depths for a wide variety of combinatorial optimization problems. We demonstrate that the GNN accurately predicts QAOA performance within a 10% margin of the true values. Furthermore, the model exhibits strong generalization capabilities across unseen problem classes, larger problem sizes, and higher layer counts. Our approach allows to identify viable problem instances for QAOA and to select an adequate parameter initialization strategy with minimal layer depth, without the need of costly parameter optimization.

quant-ph↗

arXiv2025

CleanQRL: Lightweight Single-file Implementations of Quantum Reinforcement Learning Algorithms

At the interception between quantum computing and machine learning, Quantum Reinforcement Learning (QRL) has emerged as a promising research field. Due to its novelty, a standardized and comprehensive collection for QRL algorithms has not yet been established. Researchers rely on numerous software stacks for classical Reinforcement Learning (RL) as well as on various quantum computing frameworks for the implementation of the quantum subroutines of their QRL algorithms. Inspired by the CleanRL library for classical RL algorithms, we present CleanQRL, a library that offers single-script implementations of many QRL algorithms. Our library provides clear and easy to understand scripts that researchers can quickly adapt to their own needs. Alongside ray tune for distributed computing and streamlined hyperparameter tuning, CleanQRL uses weights&biases to log important metrics, which facilitates benchmarking against other classical and quantum implementations. The CleanQRL library enables researchers to easily transition from theoretical considerations to practical applications.

quant-ph↗

arXiv2025

Quantum-Efficient Kernel Target Alignment

In recent years, quantum computers have emerged as promising candidates for implementing kernels. Quantum Embedding Kernels embed data points into quantum states and calculate their inner product in a high-dimensional Hilbert Space by computing the overlap between the resulting quantum states. Variational Quantum Circuits (VQCs) are typically used for this end, with Kernel Target Alignment (KTA) as cost function. The optimized kernels can then be deployed in Support Vector Machines (SVMs) for classification tasks. However, both classical and quantum SVMs scale poorly with increasing dataset sizes. This issue is exacerbated in quantum kernel methods, as each inner product requires a quantum circuit execution. In this paper, we investigate KTA-trained quantum embedding kernels and employ a low-rank matrix approximation, the Nystr\"om method, to reduce the quantum circuit executions needed to construct the Kernel Matrix. We empirically evaluate the performance of our approach across various datasets, focusing on the accuracy of the resulting SVM and the reduction in quantum circuit executions. Additionally, we examine and compare the robustness of our model under different noise types, particularly coherent and depolarizing noise.

quant-ph↗

arXiv2025

Benchmarking Quantum Reinforcement Learning

Quantum Reinforcement Learning (QRL) has emerged as a promising research field, leveraging the principles of quantum mechanics to enhance the performance of reinforcement learning (RL) algorithms. However, despite its growing interest, QRL still faces significant challenges. It is still uncertain if QRL can show any advantage over classical RL beyond artificial problem formulations. Additionally, it is not yet clear which streams of QRL research show the greatest potential. The lack of a unified benchmark and the need to evaluate the reliance on quantum principles of QRL approaches are pressing questions. This work aims to address these challenges by providing a comprehensive comparison of three major QRL classes: Parameterized Quantum Circuit based QRL (PQC-QRL) (with one policy gradient (QPG) and one Q-Learning (QDQN) algorithm), Free Energy based QRL (FE-QRL), and Amplitude Amplification based QRL (AA-QRL). We introduce a set of metrics to evaluate the QRL algorithms on the widely applicable benchmark of gridworld games. Our results provide a detailed analysis of the strengths and weaknesses of the QRL classes, shedding light on the role of quantum principles in QRL and paving the way for future research in this field.

quant-ph↗

arXiv2024

Hamiltonian-based Quantum Reinforcement Learning for Neural Combinatorial Optimization

Advancements in Quantum Computing (QC) and Neural Combinatorial Optimization (NCO) represent promising steps in tackling complex computational challenges. On the one hand, Variational Quantum Algorithms such as QAOA can be used to solve a wide range of combinatorial optimization problems. On the other hand, the same class of problems can be solved by NCO, a method that has shown promising results, particularly since the introduction of Graph Neural Networks. Given recent advances in both research areas, we introduce Hamiltonian-based Quantum Reinforcement Learning (QRL), an approach at the intersection of QC and NCO. We model our ansatzes directly on the combinatorial optimization problem's Hamiltonian formulation, which allows us to apply our approach to a broad class of problems. Our ansatzes show favourable trainability properties when compared to the hardware efficient ansatzes, while also not being limited to graph-based problems, unlike previous works. In this work, we evaluate the performance of Hamiltonian-based QRL on a diverse set of combinatorial optimization problems to demonstrate the broad applicability of our approach and compare it to QAOA.

quant-ph↗

arXiv2023

Variational Quantum Circuit Design for Quantum Reinforcement Learning on Continuous Environments

Quantum Reinforcement Learning (QRL) emerged as a branch of reinforcement learning (RL) that uses quantum submodules in the architecture of the algorithm. One branch of QRL focuses on the replacement of neural networks (NN) by variational quantum circuits (VQC) as function approximators. Initial works have shown promising results on classical environments with discrete action spaces, but many of the proposed architectural design choices of the VQC lack a detailed investigation. Hence, in this work we investigate the impact of VQC design choices such as angle embedding, encoding block architecture and postprocessesing on the training capabilities of QRL agents. We show that VQC design greatly influences training performance and heuristically derive enhancements for the analyzed components. Additionally, we show how to design a QRL agent in order to solve classical environments with continuous action spaces and benchmark our agents against classical feed-forward NNs.

quant-ph↗

arXiv2023

Restricted Global Optimization for QAOA

The Quantum Approximate Optimization Algorithm (QAOA) has emerged as a promising variational quantum algorithm for addressing NP hard combinatorial optimization problems. However, a significant limitation lies in optimizing its classical parameters, which is in itself an NP hard problem. To circumvent this obstacle, initialization heuristics, enhanced problem encodings and beneficial problem scalings have been proposed. While such strategies further improve QAOA's performance, their remaining problem is the sole utilization of local optimizers. We show that local optimization methods are inherently inadequate within the complex cost landscape of QAOA. Instead, global optimization techniques greatly improve QAOA's performance across diverse problem instances. While global optimization generally requires high numbers of function evaluations, we demonstrate how restricted global optimizers still show better performance without requiring an exceeding amount of function evaluations.

quant-ph↗

arXiv2023

Parameter Optimization of LLC-Converter with multiple operation points using Reinforcement Learning

The optimization of electrical circuits is a difficult and time-consuming process performed by experts, but also increasingly by sophisticated algorithms. In this paper, a reinforcement learning (RL) approach is adapted to optimize a LLC converter at multiple operation points corresponding to different output powers at high converter efficiency at different switching frequencies. During a training period, the RL agent learns a problem specific optimization policy enabling optimizations for any objective and boundary condition within a pre-defined range. The results show, that the trained RL agent is able to solve new optimization problems based on LLC converter simulations using Fundamental Harmonic Approximation (FHA) within 50 tuning steps for two operation points with power efficiencies greater than 90%. Therefore, this AI technique provides the potential to augment expert-driven design processes with data-driven strategy extraction in the field of power electronics and beyond.

cs.LG↗