Machine learning as an enabler of qubit scalability

Jie Pan

Tomás Martínez, Sergi

Quantumcomputers exhibit significant potential for addressing problems that are intractable by classical computing. Nevertheless, the scalability of quantum architectures remains a pivotal challenge within the field. Current efforts for increasing the number of qubits. However, using these architectures implies dealing with new hardware and algorithmic challenges. The primary focus of this thesis is the partitioning of quantum circuits across multiple cores; a task classified as an NP-hard problem. While classical algorithms often struggle with execution time and scalability, Machine Learning (ML) has emerged as a promising, faster yet powerful alternative. This thesis presents a novel approach for circuit partitioning in multi-core quantum architectures using Deep Reinforcement Learning (DRL) with graph neural networks (GNN). This methodology provides a flexible and efficient framework, enabling the partitioning of circuits with varying numbers of qubits while maintaining high performance and scalability.

Tiffany Khou, Christopher S. Stuetzle

Jincheng Zhang

This paper introduces a novel self-adaptive machine learning algorithm based on quantum geometry. Traditional machine learning algorithms often rely on handcrafted models, limiting their adaptability and scalability. Quantum geometry, a theoretical framework that describes the fundamental structure of spacetime, offers a unique perspective for representing and manipulating complex data. This work proposes a new algorithm that leverages quantum geometry to enhance the accuracy and efficiency of machine learning models, focusing on model scalability and adaptability. The core mechanism involves mapping data points onto a quantum geometric representation, enabling the algorithm to dynamically adjust its parameters to optimize performance. We demonstrate the effectiveness of this approach through a series of experiments and analysis, highlighting its potential to overcome limitations of conventional machine learning. This research explores the benefits of utilizing quantum geometry in accelerating and improving machine learning processes.

Abhishek Nachankar, Amartya Choubey, Amit Gond +5 more

Quantum Machine Learning (QML):An emerging research area that integrates principles of quantum computing with machine learning algorithms to enhance computational efficiency, scalability, and learning capability for complex data-driven problems. Cloud-Based Quantum Computing:A computing paradigm that provides remote access to quantum processors and simulators through cloud platforms, enabling scalable, cost-effective, and accessible quantum experimentation without the need for dedicated quantum hardware. Hybrid Quantum–Classical Models:Machine learning architectures that combine classical data preprocessing and optimization techniques with quantum circuits to leverage the strengths of both classical and quantum computation. Weather Forecasting:The process of predicting atmospheric conditions such as temperature, humidity, pressure, and wind speed using data-driven models and computational techniques. Variational Quantum Circuits (VQC):Parameterized quantum circuits optimized using classical algorithms, widely used in quantum machine learning for classification and regression tasks on Noisy Intermediate-Scale Quantum (NISQ) devices. NISQ Devices:Current-generation quantum computers characterized by limited qubit counts and noise, which influence the performance and accuracy of present-day quantum algorithms.