Model Releases
Resolution-Consistent Greedy Neural Approximation on Infinite-Dimensional Spaces
arXiv:2608.20812v1 Announce Type: new Abstract: We develop constructive approximation and learning guarantees for shallow neural models with infinite-dimensional inputs observed through finitely many
arXiv:2608.20812v1 Announce Type: new Abstract: We develop constructive approximation and learning guarantees for shallow neural models with infinite-dimensional inputs observed through finitely many coordinates. The analysis is based on a parameter-normalized neural dictionary and its associated weighted variation class. Within this class, the approximation error separates into a distribution-dependent coordinate-truncation term and a greedy finite-width term. For empirical regression, a fully-corrective greedy procedure yields population guarantees whose statistical complexity is uniform in the retained input resolution. The same framework extends to Hilbert-valued responses without an explicit dependence on the output dimension. The dimension-free statements are statistical, not computational: selecting a new neuron still requires solving a nonconvex parameter-search problem. The quasi-Polish construction underlying recent infinite-dimensional universal approximation results provides a motivating example, and synthetic experiments illustrate the predicted resolution, width, and sample-size regimes.
Related
- Quantitative Sobolev Approximation Bounds for Neural Operators with Empirical Validation on Burgers Equation
- Representation Costs in Data Science: Foundations and the Quasi-Banach Spaces of Deep Neural Networks
- Test-time Generalization for Physics through Neural Operator Splitting
Source: arXiv cs.LG | 2026-08-24