Journal of Mathematical Learning and Computation

The Journal of Mathematical Learning and Computation (JMLC) provides a multidisciplinary forum for advancing the mathematical, computational, and algorithmic foundations of learning systems. The journal welcomes contributions that bridge rigorous theory and practical computation, with emphasis on mathematics-inspired learning methods, computational innovation, and applications in data- and imaging-driven sciences.

Journal Scope

JMLC covers (but is not limited to) the following areas:
• Mathematical foundations of learning: variational methods, partial differential equations, stochastic processes, optimization theory, and information geometry for learning models.
• Computational learning theory and algorithms: generalization theory, optimization dynamics, stochastic algorithms, approximation theory, and mathematically inspired architectures.
• Learning in imaging, vision, and multimodal data: inverse problems, mathematical imaging, multimodal and high-dimensional data analysis, and AI-enhanced imaging systems.
• Mathematics-inspired machine learning: geometry-, topology-, or physics-informed learning frameworks; hybrid model- and data-driven approaches.
• Simulation and data science applications: mathematics-guided learning for physical modeling, medicine, engineering, and multimodal data fusion.
• Interdisciplinary bridges: uniting mathematical rigor with computational advances to create new paradigms of learning across science and engineering.
• Novel mathematics-based methods with open software: development of new learning algorithms, computational frameworks, or mathematical models, accompanied by open-source implementations to promote reproducibility, accessibility, and practical adoption.

Journal Aim

By uniting mathematical learning theory with computational practice, JMLC seeks to establish a home for rigorous research at the intersection of mathematics, computation, and data-driven sciences, and to foster cross-disciplinary innovation in the design and understanding of learning systems. JMLC encourages contributions that combine rigorous mathematical theory with computational innovation, including the development of novel methods accompanied by open software to ensure reproducibility and enable broader adoption.