565 citations · 4k across the 52 of their papers we have counts for
Showing 2015Show all
3 papers · 1 filter
cs.LG2015★ 4 cited
Data-Dependent Path Normalization in Neural Networks
Behnam Neyshabur, Ryota Tomioka, Ruslan Salakhutdinov +1
We propose a unified framework for neural net normalization, regularization and optimization, which includes Path-SGD and Batch-Normalization and interpolates between them across t…
cs.LG2015★ 163 cited
Path-SGD: Path-Normalized Optimization in Deep Neural Networks
Behnam Neyshabur, Ruslan Salakhutdinov, Nathan Srebro
We revisit the choice of SGD for training deep neural networks by reconsidering the appropriate geometry in which to optimize the weights. We argue for a geometry invariant to resc…
cs.LG2015★ 75 cited
Norm-Based Capacity Control in Neural Networks
Behnam Neyshabur, Ryota Tomioka, Nathan Srebro
We investigate the capacity, convexity and characterization of a general family of norm-constrained feed-forward networks.