Machine learning methods for quantum mechanics

Scott Lawerence, Yukari Yamauchi, Hyunwoo Oh, Semeon Valgushev

Published Jan 1, 2024• 0 citations

Abstract

Exploratory implementations of possible algorithms for simulating small quantum mechanical systems on a classical computer.

DOI: 10.11578/dc.20240322.7

Related papers

Quantum Machine Learning Approaches

P. Mangalraj, Ganesh Kumar Natarajan, S. Iniyan +1 more

The rise of machine learning algorithms in multidisciplinary areas is inevitable. Quantum computers are a significant recent area of development where complex algorithms can be efficiently executed for better performance. Implementing complex algorithms in quantum machines for hardware support systems is escalating due to the emergence of robotics and automated systems in all domains. The acceleration of artificial systems in hardware-based systems requires special approaches, and quantum approaches are more successful in devising accelerated hybrid systems. This chapter mainly deals with the approaches to implementing machine learning algorithms using quantum computing. The chapter was initiated with the question: “Why is quantum computing required to implement machine learning algorithms?” The major hiccup in implementing any machine learning algorithm in classical systems is the complexity of the algorithms. High dimensionality is a curse in implementing machine learning algorithms in classical systems. Quantum computing is a rescuing angel to address the issue of high dimensionality using parallelism. Quantum mechanics is well-versed in generating counterintuitive patterns. The deep learning paradigms identify the data patterns and vice versa by generating similar patterns. Classical machine learning suffers by generating patterns from the quantum of data or information, whereas the quantum mechanism succeeds by implementing the same algorithm using the quantum mechanism. The potential of the quantum mechanism to overcast some of the specific problems by its implementation strategy is called quantum potential, and the strategy used to increase the quantum potential is called the quantum algorithm. The chapter deals with the complexity of quantum computing mechanisms while implementing machine learning algorithms as the prima facie. Following the complexity analysis, usage of feature maps and extraction in the quantum mechanism is discussed for a clear understanding. Quantum embedding techniques are discussed prior to algorithms used to implement machine learning in quantum computers. The remaining sections of the chapter introduces Deutch-Jozsa, HHL, QUBO quantum mechanism-based algorithms and the execution of conventional machine learning algorithms such as principal component analysis (PCA), K-Means, K-Medians, and Support Vector Machines (SVM). Critical emphasis is placed on solving NP-Hard problems using quantum mechanisms for addressing real-time problems. This chapter helps readers to implement quantum approaches for applying machine learning algorithms in large-scale systems. This chapter deals with the main concepts in understanding quantum computing for machine learning systems, and major algorithms and foundations have been discussed for better understanding of quantum computing in machine learning.

Chapman & Hall/CRC eBooksOct 1, 20240 citations

Machine Learning as a Tool to Teach Quantum Mechanics

Huber Nieto-Chaupis

IEEE/ACIS International Conference on Software Engineering Research, Management and Applications (SERA)May 1, 20260 citations

Machine Learning Approaches to Quantum Computing and Quantum Information Processing

Suman Thapaliya, Dipesh Neupane, Manoj Bhattarai

May 9, 20260 citations

Scalable quantum simulations of molecular systems via improved optimization of neural quantum states

Guang-Ze Zhang, Jia-Cheng Huang, Lian‐Wei Ye +2 more

Quantum simulations of molecular systems hold transformative potential for computational chemistry, yet optimization inefficiencies and classical computational bottlenecks hinder practical implementation. We present algorithmic enhancements to the optimization of the unitary-coupled restricted Boltzmann machine Ansatz in the context of quantum machine learning, integrating adaptive learning rate and block optimization with the variational quantum imaginary time evolution algorithm. These improvements address convergence robustness and classical overhead in hybrid quantum-classical workflows. Demonstrations on small molecular systems show that our adaptive learning rate approach achieves chemically accurate results with fewer optimization steps compared to conventional methods, while block optimization further enables efficient parameter updates for larger systems, alleviating classical bottlenecks without compromising quantum expressivity. These advancements offer the possibility of extending the reach of near-term quantum hardware to scalable molecular simulations.

The Journal of Chemical PhysicsJun 11, 20250 citations

Quantum Mechanics and Machine Learning

Zongrui Pei

The Materials Research Society seriesJan 1, 20260 citations

Quantum Machine Learning: The Superhero That Classical Machine Learning Never Knew It Needed

Mahule Roy

Quantum Machine Learning (QML) is an emerging interdisciplinary field that combines the principles of quantum mechanics and machine learning to develop algorithms that can potentially outperform classical algorithms in certain tasks. QML leverages the unique properties of quantum systems, such as superposition and entanglement, to process information in ways that are not possible with classical computers. This paper provides a comprehensive overview of QML, including its principles, algorithms, and applications. We focus particularly on supervised learning methods, which involve training a quantum model on labeled data to make predictions on new, unseen data. We discuss the potential of QML to revolutionize various domains, such as finance, chemistry, and materials science, and highlight the challenges associated with the development and implementation of QML algorithms, including the need for more advanced quantum hardware and software. This paper aims to provide a clear understanding of the current state of QML research and its potential impact on future computational capabilities.

Oct 6, 20240 citations