Partially trainable networks show a sharp approximation phase transition
For spherical biased-ReLU features at d=5 and τ=10, about 4.1% trainable width captures 90% of the bound reduction.
Stories per day · 30 days
1 RSS
3 stories, newest first · one card per story
Stories tagged #approximation-theory
Singular parameters and missing limits in neural PDE solvers
Neural tanh PDE solvers can miss finite limits as parameters diverge; kernel derivatives restore attainable approximations.
A General Kernel Framework for Non-CND Distance Measures Using |D|-Dimensional Sparse Landmark Embeddings
Proposes the Sparse Landmark Embedding kernel, guaranteeing PSD kernels for arbitrary distances like geodesic and Wasserstein without CND requirements.