An abstract theorem gives dimension-independent, smoothness-improving approximation rates for shallow kernel networks, covering ReLU networks, RBFs, manifold learning, and quasirandom integration.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dimension independent bounds for general shallow networks
An abstract theorem gives dimension-independent, smoothness-improving approximation rates for shallow kernel networks, covering ReLU networks, RBFs, manifold learning, and quasirandom integration.