Data-Dependent Path Normalization in Neural Networks
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Nov 2015.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 2; 2023: 0; 2024: 1; 2025: 2; 2026: 1.
6 papers.
- 2022Rethinking Normalization Methods in Federated Learningcited by 19
- 2022Batch Layer Normalization, A new normalization layer for CNNs and RNNcited by 3
- 2025Information-Theoretic Framework for Understanding Modern Machine-Learningcited by 3
- 2024A Theory of Synaptic Neural Balance: From Local to Global Ordercited by 0
- 2025Path Regularization: A Near-Complete and Optimal Nonasymptotic Generalization Theory for Multilayer Neural Networks and Double Descent Phenomenoncited by 0
- 2026Demystifying Lipschitz verification: positive matrices, negative resultscited by 0
- 2026Demystifying Lipschitz verification: positive matrices, negative results30 Mar 2026
- 2025Information-Theoretic Framework for Understanding Modern Machine-Learning9 Jun 2025
- 2025Path Regularization: A Near-Complete and Optimal Nonasymptotic Generalization Theory for Multilayer Neural Networks and Double Descent Phenomenon3 Mar 2025
- 2024A Theory of Synaptic Neural Balance: From Local to Global Order15 May 2024
- 2022Rethinking Normalization Methods in Federated Learning7 Oct 2022
- 2022Batch Layer Normalization, A new normalization layer for CNNs and RNN19 Sep 2022