2 papers
cs.LG2026
Resolution-Consistent Greedy Neural Approximation on Infinite-Dimensional Spaces
Pablo M. Berná, Antonio Falcó, Diego Mondéjar
We develop constructive approximation and learning guarantees for shallow neural models with infinite-dimensional inputs observed through finitely many coordinates. The analysis is…
math.GN2024
A universal space for finite topological spaces
Diego Mondéjar
We find universal spaces for Alexandroff and finite spaces and explore some of its topological properties as well as their description as inverse limits of finite spaces and Alexan…