Representation Costs in Data Science: Foundations and the Quasi-Banach Spaces of Deep Neural Networks
math.FA, cs.LG, math.OC, stat.ML
Submitted: 2026-06-12
Updated: 2026-09-05
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Neural reproducing kernel Banach spaces and representer theorems for deep networks
- On the inductive bias of infinite-depth ResNets and the bottleneck rank
- Deep Networks are Reproducing Kernel Chains
- Learning Sparse Compositional Functions with Norm-Constrained Neural Networks
- Lower bounds over Boolean inputs for deep neural networks with ReLU gates