Derives algorithm-dependent generalization bounds for neural nets using multilevel entropic regularization and proposes a Metropolis-simulated multi-scale Gibbs training procedure tested on a two-layer net for MNIST.
Fifty years of Shannon theory.IEEE Transactions on information theory, 44(6):2057–2078
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Nets
Derives algorithm-dependent generalization bounds for neural nets using multilevel entropic regularization and proposes a Metropolis-simulated multi-scale Gibbs training procedure tested on a two-layer net for MNIST.