A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for
Neural Networks

A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks

29 July 2017

Behnam Neyshabur

Srinadh Bhojanapalli

Papers citing "A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks"

6 / 156 papers shown

Title
Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory Ron Amit Ron Meir BDL MLT 32 173 0 03 Nov 2017
SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data Alon Brutzkus Amir Globerson Eran Malach Shai Shalev-Shwartz MLT 50 276 0 27 Oct 2017
Regularization via Mass Transportation Soroosh Shafieezadeh-Abadeh Daniel Kuhn Peyman Mohajerin Esfahani OOD 30 203 0 27 Oct 2017
Spectrally-normalized margin bounds for neural networks Peter L. Bartlett Dylan J. Foster Matus Telgarsky ODL 71 1,200 0 26 Jun 2017
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 308 2,892 0 15 Sep 2016
Norm-Based Capacity Control in Neural Networks Behnam Neyshabur Ryota Tomioka Nathan Srebro 127 577 0 27 Feb 2015