papers
Publications (2)
cs.LG2025
Operator-Theoretic Framework for Gradient-Free Federated Learning
Mohit Kumar, Mathias Brucker, Alexander Valentinitsch +4
Federated learning must address heterogeneity, strict communication and computation limits, and privacy while ensuring performance. We propose an operator-theoretic framework that…
cs.LG2024
Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent
Mohit Kumar, Alexander Valentinitsch, Magdalena Fuchs +5
This paper develops a novel mathematical framework for collaborative learning by means of geometrically inspired kernel machines which includes statements on the bounds of generali…