Showing cs.LGShow all
2 papers · 1 filter
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…
cs.LG2026
Step-Size Decay and Structural Stagnation in Greedy Sparse Learning
Pablo M. Berná
Greedy algorithms are central to sparse approximation and stage-wise learning methods such as matching pursuit and boosting. It is known that the Power-Relaxed Greedy Algorithm wit…