Fetching the paper…
Reading the bibliography…
We study the phenomenon that some modules of deep neural networks (DNNs) are more critical than others.
Generalization in deep networks: The role of distance from initialization
Nagarajan, V. and Z. Kolter (2019b) · 1901
Earlier work this paper cites.
Zhang, C., S. Bengio, and Y. Singer (2019) · 1902
Earlier work this paper cites.
Generalization bounds for deep convolutional neural networks
Long, P. and H. Sedghi (2019) · 1905
Earlier work this paper cites.
Data-dependent sample complexity of deep neural networks via Lipschitz augmentation
Wei, C. and T. Ma (2019) · 1905
Earlier work this paper cites.
A new measure of rank correlation
Kendall, M. (1938) · 1938
Earlier work this paper cites.
On information and sufficiency
Kullback, S. and R. Leibler (1951) · 1951
Earlier work this paper cites.
What size net gives valid generalization?
Baum, E. and D. Haussler (1989) · 1989
Earlier work this paper cites.
The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
Bartlett, P. (1998) · 1998
Earlier work this paper cites.
PAC-bayesian model averaging
McAllester, D. (1999) · 1999
Earlier work this paper cites.
(not) bounding the true error
Langford, J. and R. Caruana (2002) · 2002
Cited alongside, same era.
Adam: A method for stochastic optimization
Kingma, D. and J. Ba (2014) · 2014
Cited alongside, same era.
Delving deep into rectifiers: Surpassing human-level performance on imagenet classification
He, K., X. Zhang, S. Ren, and J. Sun (2015) · 2015
Cited alongside, same era.
Norm-based capacity control in neural networks
Neyshabur, B., R. Tomioka, and N. Srebro (2015) · 2015
Cited alongside, same era.
Very deep convolutional networks for large-scale image recognition
Simonyan, K. and A. Zisserman (2015) · 2015
Cited alongside, same era.
Deep residual learning for image recognition
He, K., X. Zhang, S. Ren, and J. Sun (2016) · 2016
Exploring generalization in deep learning
Neyshabur, B., S. Bhojanapalli, D. McAllester, and N. Srebro (2017) · 2017
Later among the works it cites.
PAC-Bayesian margin bounds for convolutional neural networks
Pitas, K., M. Davies, and P. Vandergheynst (2017) · 2017
Later among the works it cites.
Stronger generalization bounds for deep nets via a compression approach
Arora, S., R. Ge, B. Neyshabur, and Y. Zhang (2018) · 2018
Later among the works it cites.
A PAC-Bayesian approach to spectrally-normalized margin bounds for neural networks
Neyshabur, B., S. Bhojanapalli, and N. Srebro (2018) · 2018
Later among the works it cites.
Similarity of neural network representations revisited
Kornblith, S., M. Norouzi, H. Lee, and G. Hinton (2019) · 2019
Closest in time.
Towards understanding the role of over-parametrization in generalization of neural networks
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
Spectrally-normalized margin bounds for neural networks
Bartlett, P., D. Foster, and M. Telgarsky (2017) · 2017
Cited alongside, same era.
Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data
Dziugaite, G. K. and D. Roy (2017) · 2017
Cited alongside, same era.
Densely connected convolutional networks
Huang, G., Z. Liu, L. Van Der Maaten, and K. Weinberger (2017) · 2017
Cited alongside, same era.
Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience
Nagarajan, V. and Z. Kolter (2019a)
Cited in the paper.
Neyshabur, B., Z. Li, S. Bhojanapalli, Y. LeCun, and N. Srebro (2019) · 2019
Closest in time.
The singular values of convolutional layers
Sedghi, H., V. Gupta, and P. Long (2019) · 2019
Closest in time.
Residual learning without normalization via better initialization
Zhang, H., Y. Dauphin, and T. Ma (2019) · 2019
Closest in time.
Non-vacuous generalization bounds at the imagenet scale: a PAC-Bayesian compression approach
Zhou, W., V. Veitch, M. Austern, R. Adams, and P. Orbanz (2019) · 2019
Closest in time.