Mathematical Methods for Deep Neural Network Optimization
A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "E1: Mathematics and Computer Science".
Deadline for manuscript submissions: 20 July 2026 | Viewed by 45
Special Issue Editor
Interests: optimization theory; deep learning; machine learning; mathematical data science; adaptive computation; adaptive filtering; acoustics; inverse problems theory; Bayesian methods; system identification
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
This Special Issue will gather new theoretical insights and rigorous mathematical approaches for understanding and advancing the optimization of deep neural networks. Despite their success across various applications, deep learning models often rely on heuristic optimization strategies whose mathematical underpinnings remain only partially understood. This Special Issue will highlight recent advances in optimization methods, convergence analysis, and stability and generalization guarantees and the interplay between numerical mathematics, probability, and deep learning theory.
We particularly welcome contributions that explore optimization under non-convex landscapes, stochastic and deterministic methods, variational approaches, sparse and low-rank techniques, dynamical system perspectives, and the role of regularization in shaping learning outcomes. Submissions with applications across science, engineering, and medicine that are grounded in strong mathematical and algorithmic foundations are also encouraged.
Dr. Iman Tabatabaei Ardekani
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. Mathematics is an international peer-reviewed open access semimonthly 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.
Keywords
- deep neural networks (DNNs)
- optimization methods
- gradient descent and variants
- convex and non-convex optimization
- stochastic optimization
- variational methods
- approximation theory
- regularization techniques
- generalization and stability
- convergence analysis
- numerical linear algebra in DNNs
- sparse and low-rank methods
- differential equations and dynamical systems
- Bayesian optimization
- mathematical foundations of machine learning
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
