M. > Generalization generalization

publications (hide)33
display
all
publications only
publications per page
5
10
20
50
100
sort by
added at
title
author
publication date
entry type
help for advanced sorting...
RSS
BibTeX
RDF
more...

1On the information bottleneck theory of deep learning
A. Saxe, Y. Bansal, J. Dapello, and M. Advani. (2018)
4 years ago by @cpankow
show all tags
generalization
neuralnetwork
informationtheory
machinelearning
generalizationneuralnetworkinformationtheorymachinelearning
copydeleteadd this publication to your clipboard
2Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates
J. Negrea, M. Haghifam, G. Dziugaite, A. Khisti, and D. Roy. (2019)cite arxiv:1911.02151Comment: 23 pages, 1 figure. To appear in, Advances in Neural Information Processing Systems (33), 2019.
5 years ago by @kirk86
show all tags
readings
generalization
bounds
neurips2019
information
theory
readingsgeneralizationboundsneurips2019informationtheory
copydeleteadd this publication to your clipboard
3Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes
J. Yang, S. Sun, and D. Roy. (2019)cite arxiv:1908.07585Comment: 18 pages.
5 years ago by @kirk86
show all tags
bayesian
readings
generalization
processes
bounds
bayesianreadingsgeneralizationprocessesbounds
copydeleteadd this publication to your clipboard
3Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms
M. Haghifam, J. Negrea, A. Khisti, D. Roy, and G. Dziugaite. (2020)cite arxiv:2004.12983Comment: 17 pages.
5 years ago by @kirk86
show all tags
readings
generalization
bounds
information
theory
readingsgeneralizationboundsinformationtheory
copydeleteadd this publication to your clipboard
2Generalization bounds for deep convolutional neural networks
P. Long, and H. Sedghi. International Conference on Learning Representations, (2020)
5 years ago by @kirk86
show all tags
readings
generalization
iclr2020
bounds
readingsgeneralizationiclr2020bounds
copydeleteadd this publication to your clipboard
2In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors
J. Negrea, G. Dziugaite, and D. Roy. (2019)cite arxiv:1912.04265Comment: 12 pages.
5 years ago by @kirk86
show all tags
readings
generalization
bounds
learning
readingsgeneralizationboundslearning
copydeleteadd this publication to your clipboard
2Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data
G. Dziugaite, and D. Roy. (2017)cite arxiv:1703.11008Comment: 14 pages, 1 table, 2 figures. Corresponds with UAI camera ready and supplement. Includes additional references and related experiments.
5 years ago by @kirk86
show all tags
readings
generalization
bounds
readingsgeneralizationbounds
copydeleteadd this publication to your clipboard
1High-dimensional dynamics of generalization error in neural networks
M. Advani, and A. Saxe. (2017)cite arxiv:1710.03667.
5 years ago by @kirk86
show all tags
readings
generalization
dynamic
readingsgeneralizationdynamic
copydeleteadd this publication to your clipboard
2Linear Mode Connectivity and the Lottery Ticket Hypothesis
J. Frankle, G. Dziugaite, D. Roy, and M. Carbin. (2019)cite arxiv:1912.05671Comment: This submission subsumes 1903.01611 ("Stabilizing the Lottery Ticket Hypothesis" and "The Lottery Ticket Hypothesis at Scale").
5 years ago by @kirk86
show all tags
readings
generalization
compression
readingsgeneralizationcompression
copydeleteadd this publication to your clipboard
3Issues in Stacked Generalization
K. Ting, and I. Witten. Journal of Artificial Intelligence Research, (May 1999)
5 years ago by @becker
show all tags
nalab
comparison
stacked
generalization
r01
issues
nalabcomparisonstackedgeneralizationr01issues
copydeleteadd this publication to your clipboard
1Benign Overfitting in Linear Regression
P. Bartlett, P. Long, G. Lugosi, and A. Tsigler. (2019)cite arxiv:1906.11300.
5 years ago by @kirk86
show all tags
readings
generalization
bounds
theory
readingsgeneralizationboundstheory
copydeleteadd this publication to your clipboard
2A mathematical theory of semantic development in deep neural networks
A. Saxe, J. McClelland, and S. Ganguli. (2018)cite arxiv:1810.10531.
5 years ago by @kirk86
show all tags
deep-learning
generalization
mathematics
theory
deep-learninggeneralizationmathematicstheory
copydeleteadd this publication to your clipboard
1PAC-Bayes with Backprop
O. Rivasplata, V. Tankasali, and C. Szepesvari. (2019)cite arxiv:1908.07380.
5 years ago by @kirk86
show all tags
bayesian
readings
generalization
bounds
bayesianreadingsgeneralizationbounds
copydeleteadd this publication to your clipboard
3Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes
J. Yang, S. Sun, and D. Roy. (2019)
5 years ago by @kirk86
show all tags
complexity
generalization
bounds
neurips2019
complexitygeneralizationboundsneurips2019
copydeleteadd this publication to your clipboard
2Tradeoffs between Convergence Speed and Reconstruction Accuracy in Inverse Problems
R. Giryes, Y. Eldar, A. Bronstein, and G. Sapiro. (2016)cite arxiv:1605.09232Comment: To appear in IEEE Transactions on Signal Processing.
5 years ago by @kirk86
show all tags
complexity
readings
generalization
complexityreadingsgeneralization
copydeleteadd this publication to your clipboard
1Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?
S. Du, S. Kakade, R. Wang, and L. Yang. (2019)cite arxiv:1910.03016.
5 years ago by @kirk86
show all tags
reinforcement-learning
generalization
reinforcement-learninggeneralization
copydeleteadd this publication to your clipboard
3Fast learning rates with heavy-tailed losses
V. Dinh, L. Ho, D. Nguyen, and B. Nguyen. NIPS, (2016)
5 years ago by @kirk86
show all tags
generalization
optimization
bounds
learning
theory
generalizationoptimizationboundslearningtheory
copydeleteadd this publication to your clipboard
1The VC Dimension of Metric Balls under Fréchet and Hausdorff Distances
A. Driemel, J. Phillips, and I. Psarros. (2019)cite arxiv:1903.03211Comment: 23 pages, 5 figures.
5 years ago by @kirk86
show all tags
complexity
generalization
vc-dim
foundations
learning
theory
complexitygeneralizationvc-dimfoundationslearningtheory
copydeleteadd this publication to your clipboard
2Size-free generalization bounds for convolutional neural networks
P. Long, and H. Sedghi. (2019)cite arxiv:1905.12600.
5 years ago by @kirk86
show all tags
generalization
bounds
theory
generalizationboundstheory
copydeleteadd this publication to your clipboard
1Stabilizing the Lottery Ticket Hypothesis
J. Frankle, G. Dziugaite, D. Roy, and M. Carbin. (2019)cite arxiv:1903.01611.
5 years ago by @kirk86
show all tags
generalization
stable
sparsity
generalizationstablesparsity
copydeleteadd this publication to your clipboard

⟨⟨
⟨
1
2
⟩
⟩⟩

BibSonomy

publications (hide)33
display
all
publications only
publications per page
5
10
20
50
100
sort by
added at
title
author
publication date
entry type
help for advanced sorting...
RSS
BibTeX
RDF
more...

1On the information bottleneck theory of deep learning

2Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates

3Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes

3Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms

2Generalization bounds for deep convolutional neural networks

2In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors

2Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data

1High-dimensional dynamics of generalization error in neural networks

2Linear Mode Connectivity and the Lottery Ticket Hypothesis

3Issues in Stacked Generalization

1Benign Overfitting in Linear Regression

2A mathematical theory of semantic development in deep neural networks

1PAC-Bayes with Backprop

3Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes

2Tradeoffs between Convergence Speed and Reconstruction Accuracy in Inverse Problems

1Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?

3Fast learning rates with heavy-tailed losses

1The VC Dimension of Metric Balls under Fréchet and Hausdorff Distances

2Size-free generalization bounds for convolutional neural networks

1Stabilizing the Lottery Ticket Hypothesis

related tags

tags

publications (hide)33 displayallpublications onlypublications per page5102050100 sort byadded attitleauthorpublication dateentry typehelp for advanced sorting... RSSBibTeXRDFmore...

related tags

tags

publications (hide)33
display
all
publications only
publications per page
5
10
20
50
100
sort by
added at
title
author
publication date
entry type
help for advanced sorting...
RSS
BibTeX
RDF
more...