Quantum information theory for machine learning

Jincheng Zhang

Quantum Information-Driven Machine Learning Algorithm

Jeongho Bang, Seokwon Yoo, Jinhyoung Lee

Subodh Nath Pushpak, Sarika Jain

This paper presents an overview of quantum machine learning (QML) techniques, their approach, and their landscape. QML is a rapidly evolving field of study which has recently generated lots of interest due to improvements it promises over the classical machine learning approaches. This paper presents an overview of the application of quantum information theory on machine learning algorithms. It also discusses various designs, techniques, and algorithms of classical machine learning and quantum information theory and how they can be fused with each other. The goal of this paper is to analyze algorithms and techniques used in QML. The paper also presents some of the promising algorithms used in QML, which can be executed on a real quantum computer over cloud computing platforms with the aim to evaluate its performance based on given parameters.

Yanjun Ji

Jincheng Zhang

This paper explores the integration of Topological Information Theory (TIT) with Quantum Machine Learning (QML) to achieve quantum acceleration and data compression in machine learning. Traditional machine learning relies on explicit parameter tuning, while this integration leverages the inherent structure of topological information theory for adaptive learning. We propose a novel method for utilizing the topological structure of quantum models as a source of noise, optimizing model parameters through topological analysis to improve efficiency and generalization. The core claim is that utilizing this approach will result in enhanced quantum acceleration and data compression compared to traditional machine learning. This work presents a framework for incorporating topological information into the quantum machine learning pipeline, demonstrating a potential paradigm shift in model optimization and efficiency.

Ximing Wang

In today's data-driven society, the importance of data is ever-increasing. The ability to discern patterns and trends in this data allows us to make predictive and informed decisions. This quest for enhanced data analysis has fueled the evolution of machine learning. Quantum Machine Learning (QML) is an emerging field that seeks to amalgamate the power of quantum computing with machine learning. Despite the term quantum in its name, QML is a hybrid approach incorporating both classical and quantum processing. This fusion of classical and quantum processing enables QML to capitalize on the advantages of both. However, this integration also introduces a novel set of challenges. Here we will explore QML from computer science and physics perspectives. In the first part, the mathematical tools for machine learning and quantum theory are introduced. Then the second part will investigate how quantum computation enhances classical machine learning algorithms, with a demonstration of quantum advantages in computational complexity. The third part explores the learning of quantum models through classical optimization methods. We will find how the features of a quantum model can be learned by optimization, and how a quantum model can be trained to generate target stochastic data.