REVIEW 3 cited by
Optimal Approximation of Zonoids and Uniform Approximation by Shallow Neural Networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
abstract
We study the following two related problems. The first is to determine to what error an arbitrary zonoid in $\mathbb{R}^{d+1}$ can be approximated in the Hausdorff distance by a sum of $n$ line segments. The second is to determine optimal approximation rates in the uniform norm for shallow ReLU$^k$ neural networks on their variation spaces. The first of these problems has been solved for $d\neq 2,3$, but when $d=2,3$ a logarithmic gap between the best upper and lower bounds remains. We close this gap, which completes the solution in all dimensions. For the second problem, our techniques significantly improve upon existing approximation rates when $k\geq 1$, and enable uniform approximation of both the target function and its derivatives.
Forward citations
Cited by 3 Pith papers
-
Barron regularity of many particle Schr\"odinger eigenfunctions
Many-particle Schrödinger eigenfunctions with singular potentials are shown to lie in spectral Barron spaces up to a sharp smoothness index, giving the missing regularity theory for neural-network quantum solvers.
-
Sharp uniform approximation for spectral Barron functions by deep neural networks
ReLU networks approximate spectral Barron functions of smoothness as low as 1/2 at the N^{-1/2} rate, and L-layer networks achieve sharp N^{-sL} rates for 0<sL<=1/2.
-
Do Neural Networks Really Beat the Curse of Dimensionality? A Bit-Complexity View
When approximation quality is measured per bit instead of per parameter, neural networks do not fundamentally beat classical methods; the real limit is the metric entropy of the target function class.
Discussion (0). Continue with ORCID to comment.