Pith. sign in

Data-Dependent Path Normalization in Neural Networks

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

We propose a unified framework for neural net normalization, regularization and optimization, which includes Path-SGD and Batch-Normalization and interpolates between them across two different dimensions. Through this framework we investigate issue of invariance of the optimization, data dependence and the connection with natural gradients.

fields

stat.ML 1

years

2019 1

verdicts

CONDITIONAL 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.

  • Towards Better Generalization: BP-SVRG in Training Deep Neural Networks stat.ML · 2019-08-18 · conditional · none · ref 23 · internal anchor

    A sign-flipped SVRG variant called BP-SVRG adds stochastic-gradient noise instead of cancelling it, and empirically generalizes better than standard SVRG and often better than SGD on CIFAR and SVHN image classifiers.