Special Issue "Information-Theoretic Causal Inference and Discovery"

Dear Colleagues,

Causal inference is one of the main focus areas in artificial intelligence (AI) and machine learning (ML). Causality has received significant interest in ML in the recent years in part due to its utility for generalization and robustness. It is also central for tackling decision-making problems such as bandit problems, reinforcement learning, policy, or experimental design. Information-theoretic assumptions and techniques open new avenues for causality research ranging from discovery to inference. Some examples of the success of information theory in causal inference are the use of directed information, minimum entropy couplings and common entropy for bivariate causal discovery, the use of the information bottleneck principle with applications in the generalization of machine learning models, and analyzing causal structures of deep neural networks with information theory, among others.

This Special Issue focuses on bringing information theory and causality together to expand the scope of current causal reasoning algorithms. The expected contributions range from the introduction of new assumptions to pave the way for better analyses to addressing a causal question in a well-studied setting using a novel information-theoretic approach. Some applications include causal graph discovery and the identification of interventional or counterfactual distributions from data.

Dr. Murat Kocaoglu
Guest Editor

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.

• causal graphs
• causal discovery
• causal inference
• experimental design
• information theory
• entropy