English

Data-Dependent Path Normalization in Neural Networks

Machine Learning 2016-01-20 v4

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.

Keywords

Cite

@article{arxiv.1511.06747,
  title  = {Data-Dependent Path Normalization in Neural Networks},
  author = {Behnam Neyshabur and Ryota Tomioka and Ruslan Salakhutdinov and Nathan Srebro},
  journal= {arXiv preprint arXiv:1511.06747},
  year   = {2016}
}

Comments

17 pages, 3 figures

R2 v1 2026-06-22T11:50:50.521Z