Variational inference for sparse deep ReLU networks achieves near-minimax rates for Hölder regression functions, matching exact Bayesian inference.
A convergence theory for deep learning via over-parameterization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Convergence Rates of Variational Inference in Sparse Deep Learning
Variational inference for sparse deep ReLU networks achieves near-minimax rates for Hölder regression functions, matching exact Bayesian inference.