3 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.GT2021
Polyhedral expansions of compacta associated to finite approximations
Diego Mondéjar
This paper introduces some inverse sequences of different polyhedra all based on finite approximations of a compact metric space so they can be used to capture the shape type of th…
math.FA2021
A functional characterization of almost greedy and partially greedy bases
Pablo M. Berná, Diego Mondéjar
In 2003, S. J. Dilworth et al. ([8]) introduced the notion of almost-greedy (resp. partially-greedy) bases. These bases were characterized in terms of quasi-greediness and democrac…