Deep VIB is a neural-network parameterization of the information bottleneck objective trained via variational inference and the reparameterization trick, yielding improved generalization and adversarial robustness.
On the relation between identifiability, differential privacy and Mutual-Information privacy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2016 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Deep Variational Information Bottleneck
Deep VIB is a neural-network parameterization of the information bottleneck objective trained via variational inference and the reparameterization trick, yielding improved generalization and adversarial robustness.