Over-parameterized shallow neural operators trained by gradient descent converge linearly to the global minimum of the empirical loss under mild sample conditions.
Optimal approximation rate of relu networks in terms of width and depth,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Convergence analysis of wide shallow neural operators within the framework of Neural Tangent Kernel
Over-parameterized shallow neural operators trained by gradient descent converge linearly to the global minimum of the empirical loss under mild sample conditions.