Depth-L ReLU networks with weight decay have native function spaces that are (2/L)-normable quasi-Banach spaces — the induced regularizer is not a norm for L > 2.
Neural reproducing kernel banach spaces and representer theorems for deep networks.arXiv preprint arXiv:2403.08750, 2024
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Establishes well-posedness, propagation of chaos in Wasserstein-1, and exponential stability for stochastic mean-field dynamics on torus times probability measures under locally Lipschitz drifts.
citing papers explorer
-
Representation Costs in Data Science: Foundations and the Quasi-Banach Spaces of Deep Neural Networks
Depth-L ReLU networks with weight decay have native function spaces that are (2/L)-normable quasi-Banach spaces — the induced regularizer is not a norm for L > 2.
-
Gradient Mean-Field Dynamics with Measure-Valued States: Well-Posedness, Chaos, and Long-Time Stability
Establishes well-posedness, propagation of chaos in Wasserstein-1, and exponential stability for stochastic mean-field dynamics on torus times probability measures under locally Lipschitz drifts.