Extrapolating Learning Curves of Deep Neural Networks

By Tobias Domhan, Jost Tobias Springenberg, Frank Hutter. 2014

15 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Yoshua Bengio
2. Sergey Levine
3. Bobak Shahriari
4. Frank Hutter
5. Ziyun Wang
6. Trevor Darrell
7. Ruslan Salakhutdinov
8. Quoc V. Le

Citations in the corpus

• Taking the Human Out of the Loop: A Review of Bayesian Optimization (2016, positive): “[47], [48] built a basis set manually based on previously collected training curves.”
• Hyperopt-Sklearn: Automatic Hyperparameter Configuration for Scikit-Learn (2014, background): “Techniques for recognizing bad performers early could speed up search enormously [Swe14], [Dom14].”
• Bayesian Optimization with Tree-structured Dependencies (2017, background): “A recent line of work has been focusing on leveraging this property to speed up Bayesian optimization (Swersky et al., 2013; 2014b; Domhan et al., 2014; Li et al., 2016; Klein et al., 2016).”
• Beyond Manual Tuning of Hyperparameters (2015, methodology): “This has triggered recent methods that automatically mimic this behavior for training deep learning methods [16, 66].”
• Automated Machine Learning: Methods, Systems, Challenges (2019, unknown): “Gravity gravity(X) Inter-class dispersion [5]”