PD Dr.

Lorenz, Jeanette Miriam

Filters
Reset filters

Settings
Now showing 1 - 8 of 8
No Thumbnail Available
Publication

Benchmarking Quantum Generative Learning: A Study on Scalability and Noise Resilience using QUARK

2024 , Kiwit, Florian J. , Wolf, Maximilian A. , Marso, Marwa , Ross, Philipp , Lorenz, Jeanette Miriam , Riofrío, Carlos A. , Luckow, Andre

Quantum computing promises a disruptive impact on machine learning algorithms, taking advantage of the exponentially large Hilbert space available. However, it is not clear how to scale quantum machine learning (QML) to industrial-level applications. This paper investigates the scalability and noise resilience of quantum generative learning applications. We consider the training performance in the presence of statistical noise due to finite-shot noise statistics and quantum noise due to decoherence to analyze the scalability of QML methods. We employ rigorous benchmarking techniques to track progress and identify challenges in scaling QML algorithms, and show how characterization of QML systems can be accelerated, simplified, and made reproducible when the QUARK framework is used. We show that QGANs are not as affected by the curse of dimensionality as QCBMs and to which extent QCBMs are resilient to noise.

View
No Thumbnail Available
Publication

Recommending Solution Paths for Solving Optimization Problems with Quantum Computing

2023 , Poggel, Benedikt , Quetschlich, Nils , Burgholzer, Lukas , Wille, Robert , Lorenz, Jeanette Miriam

Solving real-world optimization problems with quantum computing requires choosing between a large number of options concerning formulation, encoding, algorithm and hardware. Finding good solution paths is challenging for end users and researchers alike. We propose a framework designed to identify and recommend the best-suited solution paths in an automated way. This introduces a novel abstraction layer that is required to make quantum-computing-assisted solution techniques accessible to end users without requiring a deeper knowledge of quantum technologies. State-of-the-art hybrid algorithms, encoding and decomposition techniques can be integrated in a modular manner and evaluated using problem-specific performance metrics. Equally, tools for the graphical analysis of variational quantum algorithms are developed. Classical, fault tolerant quantum and quantum-inspired methods can be included as well to ensure a fair comparison resulting in useful solution paths. We demonstrate and validate our approach on a selected set of options and illustrate its application on the capacitated vehicle routing problem (CVRP). We also identify crucial requirements and the major design challenges for the proposed abstraction layer within a quantum-assisted solution workflow for optimization problems.

View
No Thumbnail Available
Publication

Bessere KI-Algorithmen durch Quantencomputing?

2022 , Lorenz, Jeanette Miriam

Künstliche Intelligenz (KI) wird in der medizinischen Bildgebung immer wichtiger - beispielsweise verspricht sie Unterstützung bei Routineaufgaben und eine hohe Diagnosequalität. Für Dr. habil. Jeanette Lorenz, Senior Scientist am Fraunhofer IKS, stehen jedoch häufig zu wenig Trainingsdaten für die medizinische KI zur Verfügung. Der Einsatz von Quantencomputing hat ihrer Meinung nach das Potenzial, unterstützend einzugreifen und die Algorithmenqualität entscheidend zu verbessern.

View
No Thumbnail Available
Publication

Variational Quantum Circuit Design for Quantum Reinforcement Learning on Continuous Environments

2024 , Kruse, Georg , Dragan, Theodora-Augustina , Wille, Robert , Lorenz, Jeanette Miriam

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.

View
No Thumbnail Available
Publication

Quantum-classical convolutional neural networks in radiological image classification

2022 , Matic, Andrea , Monnet, Maureen , Schachtner, Balthasar , Lorenz, Jeanette Miriam , Messerer, Thomas

Quantum machine learning is receiving significant attention currently, but its usefulness in comparison to classical machine learning techniques for practical applications remains unclear. However, there are indications that certain quantum machine learning algorithms might result in improved training capabilities with respect to their classical counterparts - which might be particularly beneficial in situations with little training data available. Such situations naturally arise in medical classification tasks. Within this paper, different hybrid quantum-classical convolutional neural networks (QCCNN) with varying quantum circuit designs and encoding techniques are proposed. They are applied to two- and three-dimensional medical imaging data, e.g. featuring different, potentially malign, lesions in computed tomography scans. The performance of these QCCNNs is already similar to the one of their classical counterparts therefore encouraging further studies towards the direction of applying these algorithms within medical imaging tasks.

View
No Thumbnail Available
Publication

QuaST Software for Quantum Computing- Easing Solutions for Complex Optimization Problems

2022 , Lorenz, Jeanette Miriam , Ehm, Hans

In this talk, we showcase how tools developed within the QuaST project (Quantum-enabling Services and Tools for industrial applications) will aid users in solving computationally hard industry applications using quantum computers. Today’s coding environment for quantum computers often only enables experts to develop and run quantum algorithms. QuaST aims to build a bridge from industrial challenges to quantum solutions. Together with the Fraunhofer Institutes AISEC, IKS, IIS and IISB, the Technical University of Munich, the Leibniz Supercomputing Centre, IQM, ParityQC, Infineon Technologies and DATEV, we co-design a software stack covering tools for hybrid HPC/QC algorithms for complex optimization problems, addressing topics from splitting large problems to high level mappings onto quantum hardware. By this, we target a wide range of different complex combinatorial problems such as network optimization or economical analyses. As a result of our developments, quantum computers will become more accessible such that their real advantage can be unveiled and utilized. Within this talk, we demonstrate our solutions using a representative example from the semiconductor industry. The semiconductor industry has inherently long lead times and is difficult to forecast, leading to a need in flexibility for its increasingly complex supply chain processes. Therefore, optimization is crucial to reach a competitive advantage in operational excellence. Plans and commitments for millions of external and internal orders need to be scheduled on a daily basis, resulting in huge optimization problems. By utilizing the power of quantum computers, we aim at getting results which are better optimized and more stable than those generated by current heuristics and classical solvers thus far.

View
No Thumbnail Available
Publication

A Comparative Study on Solving Optimization Problems with Exponentially Fewer Qubits

2024 , Winderl, David , Franco, Nicola , Lorenz, Jeanette Miriam

Variational quantum optimization algorithms, such as the variational quantum eigensolver (VQE) or the quantum approximate optimization algorithm (QAOA), are among the most studied quantum algorithms. In our work, we evaluate and improve an algorithm based on the VQE, which uses exponentially fewer qubits compared to the QAOA. We highlight the numerical instabilities generated by encoding the problem into the variational ansatz and propose a classical optimization procedure to find the ground state of the ansatz in fewer iterations with a better or similar objective. In addition, we propose a method to embed the linear interpolation of the MaxCut problem on a quantum device. Furthermore, we compare classical optimizers for this variational ansatz on quadratic unconstrained binary optimization and graph partitioning problems.

View
No Thumbnail Available
Publication

Quantencomputing verspricht in der Zukunft bessere Patientenversorgung im Krankenhaus

2022 , Lorenz, Jeanette Miriam

Quantencomputing (QC) wird gerne als disruptive Technologie beschrieben, die in der Zukunft zu deutlichen Beschleunigungen in bestimmten Berechnungsaufgaben führen kann. Anwendungen werden in den unterschiedlichsten Bereichen erwartet, darunter auch in der Medizin. Beispiele schließen die medizinische Bildgebung ein, oder beziehen sich darauf, die Diagnostik zu unterstützen und Behandlungen besser auf die Bedürfnisse von Patienten abzustimmen.

View