Explicit function classes are constructed where compositional approximation strictly outperforms superpositional approximation with arbitrarily large gaps.
Nonlinear Approximation
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
Shallow neural networks with time-frequency localized activations achieve dimension-independent Sobolev approximation rates of order N^{-1/2} for functions in weighted modulation spaces.
A new fourth-order conservative adaptive multiresolution average-interpolating wavelet upwind scheme is proposed for hyperbolic conservation laws in compressible flows, using asymmetric wavelets for upwind discretization and symmetric ones for adaptation.
citing papers explorer
-
Compositional Approximation Can Strictly Outperform Superpositional Approximation
Explicit function classes are constructed where compositional approximation strictly outperforms superpositional approximation with arbitrarily large gaps.
-
A Fourth-order Conservative Adaptive Multiresolution Wavelet Upwind Scheme for Compressible Flows
A new fourth-order conservative adaptive multiresolution average-interpolating wavelet upwind scheme is proposed for hyperbolic conservation laws in compressible flows, using asymmetric wavelets for upwind discretization and symmetric ones for adaptation.
- Layer-wise Geometric Approximation Rates for Deep Networks