Randomized neural networks are claimed to approximate Sobolev functions in H^1 and H^2 at dimension-independent rates, but the key proof step (Eq. 3.12) is invalid as written.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Approximation Theory and Applications of Randomized Neural Networks for Solving High-Dimensional PDEs
Randomized neural networks are claimed to approximate Sobolev functions in H^1 and H^2 at dimension-independent rates, but the key proof step (Eq. 3.12) is invalid as written.