The Barron-Lipschitz Energy Gap and Depth Separation Phenomena in Scientific Machine Learning
Nima Rezaei, Stephan Wojtowytsch
math.AP, stat.ML
Submitted: 2026-07-28
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Onsager's conjecture for admissible weak solutions
- Penalising the biases in norm regularisation enforces sparsity
- Finite Element Methods for the Stretching and Bending of Thin Structures with Folding
- On turbulence and geometry: from Nash to Onsager
- On the Banach spaces associated with multi-layer ReLU networks: Function representation, approximation theory and gradient descent dynamics
- A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case
- Solving the Poisson Equation with Dirichlet data by shallow ReLU$^\alpha$-networks: A regularity and approximation perspective
- Optimal bump functions for shallow ReLU networks: Weight decay, depth separation and the curse of dimensionality
Related papers
- Anisotropic uncertainty principles for metaplectic operators
- Kinetic theory for Transformers and the lost-in-the-middle phenomenon
- Convergence of graph Dirichlet energies and graph Laplacians on intersecting manifolds of varying dimensions
- Fractional Parabolic Partial Differential Equations in Anisotropic Spectral Barron Spaces: Regularity and Neural Approximation
- Regularity of Second-Order Elliptic PDEs in Spectral Barron Spaces
- Determining a parabolic-elliptic-elliptic system by boundary observation of its non-negative solutions under chemotaxis background