Corpus ID: 235254669

Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation

@article{Belkin2021FitWF,
  title={Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation},
  author={Mikhail Belkin},
  journal={ArXiv},
  year={2021},
  volume={abs/2105.14368}
}
In the past decade the mathematical theory of machine learning has lagged far behind the triumphs of deep neural networks on practical challenges. However, the gap between theory and practice is gradually starting to close. In this paper I will attempt to assemble some pieces of the remarkable and still incomplete mathematical mosaic emerging from the efforts to understand the foundations of deep learning. The two key themes will be interpolation, and its sibling, over-parameterization… Expand

References

SHOWING 1-10 OF 105 REFERENCES
Deep learning: a statistical viewpoint
Uniform convergence may be unable to explain generalization in deep learning
Do Deeper Convolutional Networks Perform Better?
The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning
To understand deep learning we need to understand kernel learning
Harmless interpolation of noisy data in regression
Understanding overfitting peaks in generalization error: Analytical risk curves for l2 and l1 penalized interpolation
  • P. Mitra
  • Computer Science, Physics
  • ArXiv
  • 2019
Loss landscapes and optimization in over-parameterized non-linear systems and neural networks
...
1
2
3
4
5
...