Applications of Information Theory to Machine Learning

Dear Colleagues,

Machine learning applications are prevalent across various domains, representing intricate and sophisticated systems. Examples include pattern recognition, natural language processing, recommendation systems, and image classification, among others. The utilization of information theory to delve into the behavior of such machine learning systems, explaining and predicting their dynamics, has garnered considerable attention from both theoretical and experimental perspectives. Numerous advancements have been made in terms of applying information theory to machine learning, encompassing correlation analyses for spatial and temporal data, as well as the development of construction and clustering techniques for complex networks within this context. The driving forces behind this progress often stem from specific application areas, such as healthcare, finance, and computer vision.

However, the application of information theory to real-world machine learning data is frequently impeded by challenges such as non-stationarity and insufficient statistics. To advance further in this domain, we seek new statistical techniques grounded in information theory, enhancements to existing methodologies, and a deeper understanding of entropy's significance in complex machine learning systems. Contributions addressing any of these issues are highly encouraged.

This Special Issue aims to serve as a platform for the introduction of novel and refined information theory techniques tailored to machine learning applications. Specifically, the analysis and interpretation of compression for generalization, the use of mutual information for feature selection, information bottlenecks for representation learning, entropy-based anomaly detection, quantifying uncertainty with mutual information, theoretic information regularization for neural networks, etc., are within the scope of this Special Issue. Your contributions to this evolving field are eagerly awaited.

Dr. Bin Chen
Prof. Dr. Shu-Tao Xia
Dr. Mehul Motani
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Entropy is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• adversarial machine learning
• self-supervised learning
• sequential decision-making (bandit/reinforcement learning)
• deep learning theory
• clustering/community detection
• security and privacy in machine learning
• generative models
• decision theory
• federated learning