Corpus ID: 224820076

Learning Curves for Analysis of Deep Networks

@article{Hoiem2020LearningCF,
  title={Learning Curves for Analysis of Deep Networks},
  author={Derek Hoiem and Tanmay Gupta and Zhizhong Li and Michal Shlapentokh-Rothman},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.11029}
}
A learning curve models a classifier's test error as a function of the number of training samples. Prior works show that learning curves can be used to select model parameters and extrapolate performance. We investigate how to use learning curves to analyze the impact of design choices, such as pre-training, architecture, and data augmentation. We propose a method to robustly estimate learning curves, abstract their parameters into error and data-reliance, and evaluate the effectiveness of… Expand

Figures and Tables from this paper

The Shape of Learning Curves: a Review
Learning Curve Theory

References

SHOWING 1-10 OF 33 REFERENCES
Learning Curves: Asymptotic Values and Rate of Convergence
Learning Multiple Layers of Features from Tiny Images
Deep Learning Scaling is Predictable, Empirically
Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
A Constructive Prediction of the Generalization Error Across Scales
A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
Deep Residual Learning for Image Recognition
Aggregated Residual Transformations for Deep Neural Networks
...
1
2
3
4
...