Mathematical, Optimization, and Computational Modeling in Machine Learning

Dear Colleagues,

Mathematical, optimization, and computational modeling are critical research areas to advance machine learning. This call for papers aims to attract high-quality work devoted to mathematical modeling, such as formulating problems, describing a system, analyzing complexity, or formulating equations for machine learning, alongside studies on the role of optimization and machine learning in influencing global optimization, feature and model selection, and resource allocation. Finally, we would like to attract work on computational modeling that improves machine learning in general, such as simulation, agent-based modeling, and data-driven strategies. These three components are the foundations for machine learning algorithms, since they provide theoretical reasoning, optimization techniques, and implementation of machine learning algorithms in simulations and the real world.

This Special Issue provides a premier venue for people working on mathematical modeling, optimization, and computational modeling trying to understand machine learning, a research area at the forefront of artificial intelligence. Studying these three areas represents an excellent opportunity for researchers who aim to progress in machine learning and artificial intelligence. We invite authors to submit groundbreaking research on any of, but not limited to, the following topics:

a) Mathematical modeling

1. Optimization techniques for machine learning
2. Mathematical foundations of machine learning
3. Information theory and machine learning
4. Geometric deep learning

b) Optimization

1. Model selection through optimization
2. Hyperparameter tuning using optimization algorithms
3. Feature selection while aiming to achieve a specific goal
4. Scheduling and resource allocation in machine learning

c) Computational modeling

1. Machine learning for scientific computing
2. Simulation-based modeling for machine learning
3. Computational modeling of neural networks and brain-inspired approaches
4. Data-driven modeling for complex systems

All papers should be submitted electronically on the website before the deadline and comply with the guidelines, standards, and format of Axioms. Submitted papers must describe previously unpublished and original research.

Prof. Dr. Gustavo Olague
Dr. Eddie Clemente
Dr. Rocío Ochoa-Montiel
Dr. Juan Villegas Cortez
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. Axioms 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 2400 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.

• mathematical modeling
• optimization
• computational modeling